© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 3273
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax elements and 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
    arraycopy
    -0.61
     betweenstory
    -0.55
    Aholisi
    -0.54
     متعلقه
    -0.53
    \{\\
    -0.50
    principalTable
    -0.49
    酒屋
    -0.48
     Meksiku
    -0.47
    VersionUID
    -0.47
    ValueStyle
    -0.46
    POSITIVE LOGITS
     vector
    1.10
    vector
    1.08
    cout
    0.99
    string
    0.86
     string
    0.82
     cout
    0.77
     pair
    0.70
    pair
    0.65
    cin
    0.65
     vectors
    0.65
    Activations Density 0.210%

    No Known Activations