© 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. 17-GEMMASCOPE-RES-16K
    11. 13447
    Prev
    Next
    INDEX
    Explanations

    the presence of significant technical or contextual markers, possibly indicating a specific structural or functional element in a dataset or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tiết
    -0.49
    godic
    -0.48
     sien
    -0.48
     carottes
    -0.43
     sẻ
    -0.41
     apos
    -0.40
    ++]=
    -0.40
    <tbody>
    -0.40
    atterns
    -0.40
     כן
    -0.39
    POSITIVE LOGITS
     GenerationType
    0.82
    '}>
    0.81
    .")
    0.79
    .",
    0.77
    '){
    0.76
    الإنجليزية
    0.76
    Diweddarwch
    0.75
    principalColumn
    0.74
    kháu
    0.73
    SharedDtor
    0.71
    Activations Density 0.021%

    No Known Activations