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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10267
    Prev
    Next
    INDEX
    Explanations

    requests for communication or contact regarding services and information

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

    before or related to contacting someone

    np_acts-logits-general · gemini-2.0-flash

    contact us for inquiries

    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
     ComVisible
    -0.78
     ModelExpression
    -0.76
     <=",
    -0.75
     فريبيس
    -0.72
     Мексичка
    -0.70
    MigrationBuilder
    -0.64
    InsertCommand
    -0.64
    TagMode
    -0.64
     wireType
    -0.61
    withId
    -0.60
    POSITIVE LOGITS
     today
    0.80
     enquiry
    0.72
     démo
    0.71
     idag
    0.67
     TODAY
    0.67
     Today
    0.64
     inquiry
    0.62
     oggi
    0.62
     aujourd
    0.61
     Enquiry
    0.61
    Activations Density 0.129%

    No Known Activations