© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 3980
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and coding concepts

    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
    expandindo
    -0.60
    ingos
    -0.56
     néz
    -0.54
    Inggris
    -0.53
     recommandée
    -0.53
    ReusableCell
    -0.52
     ujednoznacz
    -0.52
     înal
    -0.49
    ૈ
    -0.47
    Удачи
    -0.46
    POSITIVE LOGITS
     bump
    0.59
     Roskov
    0.59
    awtextra
    0.59
     dal
    0.58
     Fringe
    0.57
    bump
    0.57
     [*]
    0.56
     SEDS
    0.56
    באנגלית
    0.55
    IndentedString
    0.55
    Activations Density 2.190%

    No Known Activations