© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11657
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving operations and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical expressions with coefficients and variables, particularly in polynomial equations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    algebraic polynomial expressions featuring variables raised to powers with numeric coefficients and arithmetic operators, often within sequence or function definitions.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    mathematical expressions involving multiplication, particularly in algebraic formulas and polynomial terms.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     levier
    -0.45
     izle
    -0.43
    CHA
    -0.41
    ściu
    -0.40
    seteq
    -0.40
     들어
    -0.38
    точник
    -0.37
    iverr
    -0.37
     quæ
    -0.37
    ADORA
    -0.37
    POSITIVE LOGITS
     autorytatywna
    0.47
    InitVars
    0.45
    verifyException
    0.43
    PreferredItem
    0.43
    GOTREF
    0.43
    enterOuterAlt
    0.43
    modelBuilder
    0.41
    MethodManager
    0.40
    SequentialGroup
    0.40
     يتيمه
    0.39
    Activations Density 0.927%

    No Known Activations