© 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-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8274
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting cues in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 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
     bénévol
    -0.41
    eluarkan
    -0.37
     теа
    -0.35
    quinha
    -0.33
    msgSender
    -0.32
    ävän
    -0.32
    报记者
    -0.32
    Junior
    -0.31
     ruines
    -0.31
    Maryland
    -0.31
    POSITIVE LOGITS
    HtmlAttribute
    0.71
    principalColumn
    0.68
    EDEFAULT
    0.66
     MainAxisSize
    0.64
     rhestr
    0.64
    __(/*!
    0.63
    RenderAtEndOf
    0.60
     BoxFit
    0.59
    MigrationBuilder
    0.59
    featureID
    0.57
    Activations Density 0.209%

    No Known Activations