© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9608
    Prev
    Next
    INDEX
    Explanations

    terms related to implied warranties and liabilities in legal contexts

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

    "Imp" followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    implied, imputation, implanted, impingement

    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
     feroit
    -0.67
    ſelves
    -0.64
     enfans
    -0.63
    étoit
    -0.59
    neſs
    -0.54
     réserver
    -0.54
    RUnlock
    -0.54
    RTHOOK
    -0.54
     ſtand
    -0.54
     pouvoit
    -0.52
    POSITIVE LOGITS
     Imp
    1.66
     imp
    1.50
    Imp
    1.46
    imp
    1.36
     IMP
    1.29
     IM
    1.23
     Im
    1.16
     im
    1.16
    im
    1.14
    IMP
    1.13
    Activations Density 0.216%

    No Known Activations