© 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. 39-GEMMASCOPE-RES-16K
    11. 3291
    Prev
    Next
    INDEX
    Explanations

    patterns related to numerical data and JSON structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TRIBUN
    -0.53
     CommandType
    -0.42
     sor
    -0.42
    ruptedException
    -0.42
    يكب
    -0.40
    WithMany
    -0.40
    stdc
    -0.38
     незавершена
    -0.38
    sor
    -0.38
     Petro
    -0.37
    POSITIVE LOGITS
    5
    0.77
    PreferredItem
    0.54
     transfieras
    0.51
     cincuenta
    0.49
     Weisheit
    0.48
     cinquième
    0.47
    isContained
    0.46
     fifty
    0.46
     Asegúrese
    0.46
     fifties
    0.45
    Activations Density 1.187%

    No Known Activations