© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 44473
    Prev
    Next
    INDEX
    Explanations

    references to evidence and claims in legal contexts

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

    legal arguments for charges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    》.
    -0.49
    )}.
    -0.46
    $.\\
    -0.44
    ).\\
    -0.43
    انتهای
    -0.43
    }.
    -0.42
     bezeichneter
    -0.40
     Loves
    -0.39
    ".
    -0.39
    UseVisualStyle
    -0.39
    POSITIVE LOGITS
     will
    1.07
     would
    1.02
     is
    1.00
     seems
    0.98
    서는
    0.97
     was
    0.96
    리는
    0.95
     could
    0.93
     has
    0.91
     adalah
    0.91
    Activations Density 3.446%

    No Known Activations