© 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 EvalsExportsAPI 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. 18996
    Prev
    Next
    INDEX
    Explanations

    references to software documentation or code-related terminology

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

    from followed by symbols

    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
    ChildScrollView
    -1.00
     kaarangay
    -0.99
     endwhile
    -0.83
     يتيمه
    -0.81
    tagHelperRunner
    -0.79
    يكب
    -0.79
    parsedMessage
    -0.78
    RegressionTest
    -0.77
     MainAxisSize
    -0.77
    OGND
    -0.77
    POSITIVE LOGITS
    [toxicity=0]
    0.51
    </td>
    0.48
    </i>
    0.46
    </em>
    0.42
    import
    0.38
    </b>
    0.37
    0
    0.35
    From
    0.35
    deckt
    0.34
    ly
    0.34
    Activations Density 0.026%

    No Known Activations