© 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. 12841
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols

    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
    ूरत
    -0.45
    Derp
    -0.45
    Instruments
    -0.45
    CloseOperation
    -0.45
    volent
    -0.43
    pona
    -0.43
    tivation
    -0.42
    ument
    -0.42
    waite
    -0.41
    läg
    -0.41
    POSITIVE LOGITS
    ThroughAttribute
    0.61
    SharedCtor
    0.61
    enguaje
    0.59
    resave
    0.58
     localised
    0.57
    >-->
    0.57
     ویکی‌پدی
    0.56
     Outre
    0.56
    interopRequire
    0.56
    المشاركات
    0.55
    Activations Density 5.114%

    No Known Activations