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. 1-GEMMASCOPE-RES-16K
    6. 13645
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terminology related to health or biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Voted
    -0.54
    providedIn
    -0.53
    Ucraina
    -0.50
    export
    -0.48
     oprot
    -0.47
    Extinguishing
    -0.47
     kväll
    -0.46
    MigrationBuilder
    -0.46
    Unmarshaller
    -0.45
     kveld
    -0.45
    POSITIVE LOGITS
    ving
    0.69
    原始内容存档于
    0.68
    脚注の使い方
    0.66
     calldata
    0.65
     Geschle
    0.64
     iconFacebook
    0.64
     مرئيه
    0.64
     hom
    0.62
    extAlignment
    0.61
    tella
    0.60
    Activations Density 2.351%

    No Known Activations