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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 1096
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and evidence evaluation

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

    court, trial, jury, alive, life, time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Personensuche
    -0.46
    CreateMap
    -0.41
    Schedulers
    -0.40
    ucap
    -0.39
     OFDb
    -0.38
     HEAVEN
    -0.36
    impulan
    -0.36
    دانشنامهٔ
    -0.35
    ndag
    -0.35
    Personendaten
    -0.34
    POSITIVE LOGITS
     AssemblyCompany
    0.48
    
    0.47
    RenderAtEndOf
    0.47
    ListItemIcon
    0.46
     AssemblyProduct
    0.43
    setIsLoading
    0.43
    jsxFileName
    0.43
    ValueGeneration
    0.41
     sahen
    0.41
     indisponible
    0.41
    Activations Density 0.130%

    No Known Activations