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. 91191
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming code

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

    programming conditionals

    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
    它們
    -0.39
    它们
    -0.39
     invitación
    -0.37
     juos
    -0.37
     universel
    -0.37
     armadura
    -0.36
     videre
    -0.36
     américain
    -0.36
     preocupaciones
    -0.36
     américaine
    -0.35
    POSITIVE LOGITS
    BeginContext
    0.84
     يتيمه
    0.73
    routeProvider
    0.71
    /*
    0.71
     pinulongan
    0.63
    elsif
    0.62
    ſelben
    0.61
    ɵɵelementStart
    0.61
    makeConstraints
    0.61
    ifdef
    0.60
    Activations Density 0.013%

    No Known Activations