© 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. 9-GEMMASCOPE-RES-131K
    11. 78046
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to liability and negligence

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

    superseding

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     SwitchCompat
    -0.52
     étrang
    -0.50
    béco
    -0.47
    (!__
    -0.47
     mauva
    -0.47
     DevComponents
    -0.47
    makin
    -0.45
    UnknownFields
    -0.45
     Gees
    -0.43
    yecek
    -0.42
    POSITIVE LOGITS
    sed
    2.17
    SED
    1.19
     sed
    1.19
    Sed
    1.12
     Sed
    1.09
     SED
    0.98
    ISED
    0.89
    ised
    0.82
    ses
    0.81
    seda
    0.79
    Activations Density 0.010%

    No Known Activations