Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 6752
    Prev
    Next
    INDEX
    Explanations

    occurrences of incidents or conditions related to physical injuries and their assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    +#+#
    -0.43
     Exacts
    -0.37
     Cent
    -0.35
    minde
    -0.33
    ituary
    -0.32
    โต
    -0.32
     Vie
    -0.32
    cent
    -0.31
    ्म
    -0.31
    gebnisse
    -0.31
    POSITIVE LOGITS
     tripped
    0.61
     tripping
    0.59
     transférez
    0.58
     ConstraintSet
    0.56
     slippery
    0.54
    stateProvider
    0.54
     ModelExpression
    0.53
    kwds
    0.52
    Slip
    0.52
     resourceCulture
    0.50
    Activations Density 0.365%

    No Known Activations