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. 67586
    Prev
    Next
    INDEX
    Explanations

    programming syntax for type aliases and assignment

    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
    +#+#
    -0.48
    ($__
    -0.48
    出版年
    -0.46
    viewDidLoad
    -0.43
     veckan
    -0.42
    payee
    -0.41
    ☸
    -0.41
    idenav
    -0.40
     للاسماء
    -0.40
    ghurt
    -0.40
    POSITIVE LOGITS
     Bon
    0.49
    Beantwoorden
    0.48
     ::=
    0.48
    simpleType
    0.47
     akin
    0.47
    MessageOf
    0.46
     cref
    0.46
    ⇔
    0.46
    HasColumnType
    0.45
    interface
    0.45
    Activations Density 0.002%

    No Known Activations