Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103098
    Prev
    Next
    INDEX
    Explanations

    variables and functions related to statistical and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    s
    -0.58
    c
    -0.37
     noOf
    -0.36
    er
    -0.36
    n
    -0.34
    C
    -0.34
    if
    -0.33
    //
    -0.32
    a
    -0.32
    ع
    -0.32
    POSITIVE LOGITS
     Epsilon
    1.06
     Gamma
    1.04
     Kappa
    1.02
     Sigma
    0.98
     Delta
    0.97
     Zeta
    0.94
     gamma
    0.94
     Lambda
    0.93
     DELTA
    0.92
    Kappa
    0.92
    Activations Density 0.079%

    No Known Activations