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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 111507
    Prev
    Next
    INDEX
    Explanations

    semicolons and function call syntax in code snippets

    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-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
    AndEndTag
    -0.83
    ftagPool
    -0.76
    -------
    -0.62
    withIdentifier
    -0.60
    таратура
    -0.59
     հղումներ
    -0.58
     nahilalakip
    -0.58
    Према
    -0.57
    Jîn
    -0.57
    AddTagHelper
    -0.57
    POSITIVE LOGITS
     importa
    0.30
     enfermo
    0.30
     desconocido
    0.29
     procedimiento
    0.29
     vertrou
    0.29
     Longueur
    0.29
    verlauf
    0.28
     explications
    0.28
     whether
    0.28
     Flasche
    0.28
    Activations Density 0.016%

    No Known Activations