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. 20-GEMMASCOPE-RES-16K
    6. 15676
    Prev
    Next
    INDEX
    Explanations

    references to academic reviews and summaries of research studies

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

    literature reviews or review articles

    np_acts-logits-general · gemini-2.0-flash

    review article overview

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     لكرة
    -0.57
    TabIndex
    -0.53
    Sprintf
    -0.52
     ModelExpression
    -0.50
    makeConstraints
    -0.50
    aki
    -0.45
    fortawesome
    -0.45
    acos
    -0.45
    msgTypes
    -0.44
    findpost
    -0.44
    POSITIVE LOGITS
     review
    1.84
    review
    1.67
     Review
    1.67
    Review
    1.64
     reviews
    1.64
     reviewed
    1.55
     reviewing
    1.50
     REVIEW
    1.48
     Reviews
    1.44
    reviewed
    1.43
    Activations Density 0.618%

    No Known Activations