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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8804
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation specifically related to functions and variables in equations

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

    mathematical notation in formulas, particularly coefficients and operators with subscripts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.81
    httphttps
    -0.76
     ſche
    -0.61
     wireType
    -0.56
    ſelves
    -0.54
    ConstraintMaker
    -0.54
     '\\;'
    -0.52
    RegressionTest
    -0.52
     surla
    -0.52
    pushFollow
    -0.51
    POSITIVE LOGITS
    untut
    0.35
    macam
    0.35
    hi
    0.34
     OMITTED
    0.34
    He
    0.32
     cioccolato
    0.32
     bubuk
    0.31
    ceiro
    0.30
    he
    0.30
    co
    0.30
    Activations Density 1.969%

    No Known Activations