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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 654
    Prev
    Next
    INDEX
    Explanations

    names of individuals and families in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InitVars
    -0.76
    EndInit
    -0.66
    estacks
    -0.61
    EDEFAULT
    -0.58
    urlencoded
    -0.57
    rhosis
    -0.57
    quelize
    -0.56
    asanjo
    -0.56
    createStatement
    -0.55
     Infórmanos
    -0.54
    POSITIVE LOGITS
     Danielle
    0.52
     Jessica
    0.51
     Connor
    0.51
    Jessica
    0.51
     Chloe
    0.50
    Danielle
    0.49
    Chloe
    0.48
     Micah
    0.48
    Travis
    0.47
     Brandon
    0.47
    Activations Density 0.375%

    No Known Activations