© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9875
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to penalties and liabilities

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

    Legal or statutory language

    np_acts-logits-general · gemini-2.0-flash

    such shall statute action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.45
    ''');
    -0.40
    RTLI
    -0.40
    KK
    -0.38
    Kjelder
    -0.37
    sa
    -0.36
     wacky
    -0.36
    scared
    -0.36
     Squid
    -0.36
    cilla
    -0.35
    POSITIVE LOGITS
     Administrativna
    0.60
     ModelExpression
    0.54
    enumii
    0.54
    RegressionTest
    0.50
    addGap
    0.49
    RotationOrder
    0.48
     représentation
    0.47
     bénévoles
    0.47
     législation
    0.47
     opérations
    0.46
    Activations Density 1.832%

    No Known Activations