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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 10786
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to immediate actions and urgency

    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
    IContainer
    -0.50
     فريبيس
    -0.49
    Aiheesta
    -0.49
    PageRoute
    -0.47
    PRNewswire
    -0.42
     glyphicon
    -0.40
    sproz
    -0.39
    Hentet
    -0.37
     ویکی‌پدی
    -0.37
    mappedBy
    -0.36
    POSITIVE LOGITS
    цездатний
    0.45
     immediately
    0.44
     Correction
    0.41
    Vidite
    0.41
    олові
    0.40
    immediately
    0.40
     vastaan
    0.40
     intervene
    0.39
     promptly
    0.39
    neſs
    0.39
    Activations Density 0.036%

    No Known Activations