© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12467
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and governmental actions, such as impeachment and recall processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     désolés
    -0.35
    hits
    -0.33
    wußt
    -0.33
     pioneer
    -0.32
    Conversions
    -0.32
    aroa
    -0.31
    Hits
    -0.31
     упа
    -0.30
    sold
    -0.30
     prohib
    -0.30
    POSITIVE LOGITS
    InjectAttribute
    0.58
    </tfoot>
    0.56
    XDECREF
    0.54
    manjaro
    0.49
     impeachment
    0.49
    endpush
    0.49
     ब्रेकडाउन
    0.48
     poveznice
    0.47
    AddTagHelper
    0.47
    ロウィン
    0.47
    Activations Density 0.490%

    No Known Activations