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. 20-GEMMASCOPE-RES-16K
    6. 217
    Prev
    Next
    INDEX
    Explanations

    geographical locations and names of places

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

    names of locations, counties, and geographical areas in Illinois.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    jspb
    -0.63
    __*/
    -0.55
     endblock
    -0.54
    adaptiveStyles
    -0.53
    <pad>
    -0.52
    <unused41>
    -0.52
    tonode
    -0.52
    <unused8>
    -0.52
    UnusedPrivate
    -0.52
    <unused23>
    -0.51
    POSITIVE LOGITS
     suburban
    0.69
     Suburban
    0.54
     suburb
    0.52
     suburbs
    0.51
     Westchester
    0.49
     Bekasi
    0.46
     Selangor
    0.46
     Middlesex
    0.46
     commuter
    0.43
     Tangerang
    0.42
    Activations Density 0.341%

    No Known Activations