© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 56293
    Prev
    Next
    INDEX
    Explanations

    portions of mathematical or technical formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    end of document

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -0.87
     ſei
    -0.80
    iſen
    -0.75
    ſchaft
    -0.74
    ConstraintMaker
    -0.74
    ftagPool
    -0.73
    хьтан
    -0.73
    征詢我
    -0.73
     Elden
    -0.72
     للمعارف
    -0.72
    POSITIVE LOGITS
    .
    0.56
    ↵↵
    0.55
    <eos>
    0.45
    </tr>
    0.43
    ].
    0.43
    3
    0.42
    .]
    0.41
    。
    0.41
    .}
    0.40
    </table>
    0.39
    Activations Density 0.019%

    No Known Activations