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. 91977
    Prev
    Next
    INDEX
    Explanations

    phrases related to client needs assessment and the processes involved in delivering tailored services

    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
     تضيفلها
    -0.52
     فريبيس
    -0.52
    ніципалі
    -0.42
    iprot
    -0.41
    chene
    -0.39
    Gal
    -0.37
    zeptember
    -0.37
     Naturally
    -0.37
    AndEndTag
    -0.36
     naturale
    -0.36
    POSITIVE LOGITS
    tvguidetime
    0.52
    TargetException
    0.52
     estekak
    0.48
    <?
    0.43
     AssemblyCulture
    0.42
    timedia
    0.41
     XCTest
    0.40
     interpreting
    0.40
    awtextra
    0.39
    BagConstraints
    0.38
    Activations Density 0.054%

    No Known Activations