Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 8277
    Prev
    Next
    INDEX
    Explanations

    references to academic collaborations and proceedings in scientific literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     social
    -0.59
    digitalWrite
    -0.57
    gnition
    -0.56
    prox
    -0.55
     pro
    -0.54
     Pro
    -0.51
     reserve
    -0.50
    ửa
    -0.50
    undred
    -0.49
    koc
    -0.48
    POSITIVE LOGITS
    ImageContext
    0.80
    脚注の使い方
    0.78
    ConstraintMaker
    0.72
    RenderAtEndOf
    0.72
     physicists
    0.70
    AnchorStyles
    0.67
     oint
    0.66
    XmlAccessType
    0.65
    InputBorder
    0.65
     AssemblyCulture
    0.65
    Activations Density 1.149%

    No Known Activations