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. 10777
    Prev
    Next
    INDEX
    Explanations

    key details about awards and nominations in the film industry

    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
    IntoConstraints
    -0.52
    новништво
    -0.50
    BagLayout
    -0.49
    DeleteBehavior
    -0.48
    UseVisualStyle
    -0.48
    bindingNavigator
    -0.46
    Бахар
    -0.45
    ValueGeneration
    -0.45
    AutoScale
    -0.44
     dAtA
    -0.44
    POSITIVE LOGITS
     premiered
    0.46
     entgegen
    0.44
     tytu
    0.42
     unplayable
    0.41
     Barbier
    0.40
     slated
    0.40
     prosjek
    0.40
    judul
    0.39
    ppuden
    0.39
     Pemberton
    0.39
    Activations Density 0.026%

    No Known Activations