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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 53533
    Prev
    Next
    INDEX
    Explanations

    instances of code or programming-related segments

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

    mathematical and code syntax

    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
    styleType
    -0.87
    AnimationsModule
    -0.80
    <bos>
    -0.78
     ब्रेकडाउन
    -0.72
    aarrggbb
    -0.71
     Chriftian
    -0.66
     Photocase
    -0.65
    TypedDataSet
    -0.65
     ویکی‌پدی
    -0.65
    دانشنامهٔ
    -0.65
    POSITIVE LOGITS
    </code>
    0.77
    \]
    0.60
    </u>
    0.57
    </sub>
    0.56
    </em>
    0.54
    </i>
    0.53
    }}$
    0.52
    }`
    0.50
    }\]
    0.48
    )}$
    0.47
    Activations Density 0.111%

    No Known Activations