© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7759
    Prev
    Next
    INDEX
    Explanations

    the presence of specific identifiers or markup in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PostExecute
    -0.83
     ―――――
    -0.82
    đồng
    -0.77
    MockBean
    -0.75
    ofday
    -0.73
     vPvB
    -0.73
    DllImport
    -0.72
    Демографія
    -0.71
    ecap
    -0.70
     Yal
    -0.70
    POSITIVE LOGITS
    //
    1.69
    //
    1.39
     //
    1.11
    +//
    1.08
    -//
    1.05
    ///
    0.97
    ////
    0.88
    #
    0.88
     TODO
    0.83
    ">//
    0.82
    Activations Density 0.079%

    No Known Activations