© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 956
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those representing statistics or data points

    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
     nahilalakip
    -0.60
    Tikang
    -0.58
    HasForeignKey
    -0.55
     autorytatywna
    -0.50
     }{@
    -0.49
     Patrimonio
    -0.49
     الاطلاع
    -0.48
     Edad
    -0.47
     Siglo
    -0.47
    recated
    -0.45
    POSITIVE LOGITS
     resourceCulture
    0.47
    styleType
    0.46
    OrNil
    0.42
    8
    0.41
     Aner
    0.40
    RectangleBorder
    0.40
    zzarella
    0.40
     Concurrent
    0.39
    şört
    0.39
     Oce
    0.39
    Activations Density 0.131%

    No Known Activations