© 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. 21-GEMMASCOPE-RES-16K
    11. 10767
    Prev
    Next
    INDEX
    Explanations

    HTML table data elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.74
    IntoConstraints
    -0.69
    RenderAtEndOf
    -0.65
    PerformLayout
    -0.64
     ſy
    -0.63
     SwitchCompat
    -0.61
    новништво
    -0.59
    Gemeinden
    -0.58
     lenker
    -0.58
    LookAnd
    -0.57
    POSITIVE LOGITS
    <td>
    1.29
    <th>
    0.65
    ="
    0.51
    <em>
    0.47
    ing
    0.45
     Meade
    0.44
    :
    0.43
    (
    0.43
    <code>
    0.43
    ️
    0.43
    Activations Density 0.006%

    No Known Activations