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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4761
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court cases and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioutil
    -0.44
    aarrggbb
    -0.43
    omla
    -0.41
    pantalones
    -0.41
     skrzy
    -0.41
     ghép
    -0.41
    grimas
    -0.40
    olska
    -0.40
    wahati
    -0.38
     Recife
    -0.38
    POSITIVE LOGITS
     counties
    0.74
     Jefferson
    0.65
     Counties
    0.60
     county
    0.59
     Montgomery
    0.57
     Fayette
    0.57
     Mult
    0.56
     Polk
    0.56
     Rocking
    0.55
     Greene
    0.54
    Activations Density 0.688%

    No Known Activations