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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 16079
    Prev
    Next
    INDEX
    Explanations

    database operations and queries related to user and content management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.79
     CreateTagHelper
    -0.60
     ModelExpression
    -0.59
    MENAFN
    -0.55
    ftagPool
    -0.52
     AssemblyCulture
    -0.49
    UrlResolution
    -0.48
    httphttps
    -0.48
     '\\;'
    -0.48
     actionMode
    -0.47
    POSITIVE LOGITS
    providedIn
    0.48
    adaptiveStyles
    0.42
     Hor
    0.35
    tvguidetime
    0.33
     Beck
    0.33
    мента
    0.33
    horizontalLayout
    0.33
     fhew
    0.33
     Schwä
    0.33
    ichtung
    0.33
    Activations Density 0.170%

    No Known Activations