© 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. 36-GEMMASCOPE-RES-16K
    6. 7673
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and procedural obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.95
    CloseOperation
    -0.94
     <<<<<<<<<<<<<<
    -0.86
    parsedMessage
    -0.83
    ScopeManager
    -0.80
    .*")]
    -0.76
     kasarigan
    -0.75
    httphttps
    -0.73
     informée
    -0.71
     wireType
    -0.71
    POSITIVE LOGITS
     bzw
    0.98
     or
    0.91
    /
    0.88
    —
    0.84
     beziehungs
    0.83
     —
    0.83
     –
    0.80
     или
    0.79
     (
    0.78
    -,
    0.78
    Activations Density 1.466%

    No Known Activations