© 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. 4-GEMMASCOPE-RES-16K
    6. 1749
    Prev
    Next
    INDEX
    Explanations

    references to specific software or hardware models, particularly in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     matang
    -0.50
    oirs
    -0.49
    Geplaatst
    -0.46
    tubers
    -0.44
    tvguidetime
    -0.44
     Jeune
    -0.44
    achts
    -0.43
    Roblox
    -0.43
    dymyr
    -0.43
     aDecoder
    -0.43
    POSITIVE LOGITS
     Axiom
    0.71
    Nimbus
    0.68
     مرئيه
    0.67
    providedIn
    0.66
     Nimbus
    0.65
     الحره
    0.63
     समीक्षाओं
    0.63
    adpleegd
    0.63
    setSubject
    0.63
    hoenix
    0.61
    Activations Density 1.955%

    No Known Activations