© 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. 21-GEMMASCOPE-RES-16K
    6. 1731
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical compounds and biochemistry concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    volo
    -0.75
     disambiguazione
    -0.70
    stech
    -0.58
    taminophen
    -0.57
    lawayo
    -0.57
    OGND
    -0.56
    sing
    -0.56
    providedIn
    -0.55
    InlineData
    -0.55
    uits
    -0.54
    POSITIVE LOGITS
    kkkk
    0.97
    kkk
    0.90
     متحده
    0.79
    ets
    0.77
    KKKK
    0.75
    tanleria
    0.69
     merav
    0.68
     Skywalker
    0.67
    ⓧ
    0.67
     majeurs
    0.66
    Activations Density 0.632%

    No Known Activations