© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4322
    Prev
    Next
    INDEX
    Explanations

    mathematical notation related to functions and derivatives

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

    mathematical expressions and computational notation, particularly involving exponents, variables, and algebraic operations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    mathematical expressions with exponents, particularly when the exponent is 3 or other powers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    expandindo
    -0.71
     CreateTagHelper
    -0.70
    tagHelperRunner
    -0.65
     BoxFit
    -0.64
    InputTagHelper
    -0.63
     ModelExpression
    -0.62
    msgTypes
    -0.62
    SequentialGroup
    -0.60
    Carriera
    -0.59
    verwijspagina
    -0.59
    POSITIVE LOGITS
     volume
    0.41
    igshid
    0.36
    volume
    0.35
     Schicht
    0.32
    Volume
    0.32
     volumen
    0.32
     volumes
    0.31
     committed
    0.31
     manio
    0.30
    カク
    0.29
    Activations Density 1.277%

    No Known Activations