Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 10154
    Prev
    Next
    INDEX
    Explanations

    warnings and instructions related to medication use and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.71
    astify
    -0.64
    enterOuterAlt
    -0.63
    Autoritní
    -0.62
     typelib
    -0.62
    dafx
    -0.60
     ErrIntOverflow
    -0.58
     lenker
    -0.57
     NUKAT
    -0.57
    StoryboardSegue
    -0.57
    POSITIVE LOGITS
    ควร
    0.37
     jangan
    0.36
     olvides
    0.34
     cuidado
    0.34
    ütfen
    0.32
     décontract
    0.32
     Psicología
    0.31
     ferons
    0.31
     preferably
    0.31
     always
    0.29
    Activations Density 0.637%

    No Known Activations