© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7644
    Prev
    Next
    INDEX
    Explanations

    data structure elements related to URLs and web content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    JSON formatting or code snippets

    np_acts-logits-general · gemini-2.0-flash

    visiting the atmosphere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -0.71
    errHandler
    -0.66
    //
    -0.56
    ('.
    -0.54
     Avila
    -0.54
    $('.
    -0.52
    -//
    -0.51
    клопе
    -0.51
     $('.
    -0.51
    ///
    -0.50
    POSITIVE LOGITS
    RectangleBorder
    0.61
    )":
    0.59
     Infórmanos
    0.57
     Seeder
    0.57
     дописавши
    0.57
     مرئيه
    0.56
    poel
    0.54
    bibfield
    0.53
     Scu
    0.53
    orithmic
    0.52
    Activations Density 0.657%

    No Known Activations