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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15767
    Prev
    Next
    INDEX
    Explanations

    terms related to financial services and transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     (!_
    -0.44
    elseif
    -0.43
     stubborn
    -0.42
     rép
    -0.42
     său
    -0.41
     elseif
    -0.39
     predicated
    -0.39
    ља
    -0.39
     steep
    -0.38
    @[
    -0.37
    POSITIVE LOGITS
    Financial
    0.99
     Financial
    0.97
    Finance
    0.93
     Finance
    0.92
     finance
    0.92
     financial
    0.90
    financial
    0.90
     financière
    0.90
    finance
    0.86
     financier
    0.86
    Activations Density 0.067%

    No Known Activations