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. 20-GEMMASCOPE-RES-16K
    6. 15830
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and metrics related to biological studies and experiments

    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
    AnimationsModule
    -0.59
    webElementGuid
    -0.58
    IBOutlet
    -0.57
    Rüyada
    -0.56
    ValueStyle
    -0.52
     propOrder
    -0.50
    addPreferredGap
    -0.49
    Hochspringen
    -0.48
    IsContent
    -0.48
    ViewInit
    -0.47
    POSITIVE LOGITS
    évaluateur
    0.36
     contigo
    0.35
     Dauer
    0.32
    setzer
    0.30
    Personendaten
    0.29
    новништво
    0.29
     memand
    0.29
    rdoba
    0.29
     FetchType
    0.29
     reports
    0.28
    Activations Density 1.252%

    No Known Activations