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. 25696
    Prev
    Next
    INDEX
    Explanations

    references to legal counsel, organizations, and their roles within various sectors

    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
     câte
    -0.47
    MemoryWarning
    -0.47
    AnchorStyles
    -0.46
     iconTwitter
    -0.44
    AppMethodBeat
    -0.44
    Дереккөздер
    -0.44
     незавершена
    -0.43
     الاطلاع
    -0.42
     <>",
    -0.42
    InitVars
    -0.40
    POSITIVE LOGITS
     betweenstory
    0.43
     Association
    0.43
     associ
    0.42
    KommentareTeilen
    0.41
     professionals
    0.41
     Ahl
    0.41
    hebt
    0.40
    kömm
    0.40
    WebElementEntity
    0.40
     Kod
    0.40
    Activations Density 0.022%

    No Known Activations