© 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. 41-GEMMASCOPE-RES-16K
    11. 7053
    Prev
    Next
    INDEX
    Explanations

    phrases that express danger or alarming situations related to health or safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...»
    -0.61
    ...
    -0.57
    ...'
    -0.52
    '...
    -0.50
    Doesn
    -0.50
    doesn
    -0.49
    ...
    -0.49
    MigrationBuilder
    -0.49
    Didn
    -0.47
    didn
    -0.47
    POSITIVE LOGITS
     https
    0.79
     Anderson
    0.66
     Herbs
    0.63
    https
    0.60
     http
    0.59
    Anderson
    0.56
     ANDERSON
    0.55
     Zhao
    0.54
     Diario
    0.52
     Drugs
    0.52
    Activations Density 0.027%

    No Known Activations