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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84503
    Prev
    Next
    INDEX
    Explanations

    specific system signals and error codes related to process management and biological terms

    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
    SourceChecksum
    -0.65
     متعلقه
    -0.59
    :✨
    -0.56
    StoryboardSegue
    -0.54
     يتيمه
    -0.53
     IBOutlet
    -0.52
    AddTagHelper
    -0.50
    jooq
    -0.50
    VYMaps
    -0.50
    ANTLR
    -0.50
    POSITIVE LOGITS
    ButtonModule
    1.91
    MatButtonModule
    1.81
    MatIconModule
    1.35
    IconModule
    1.34
    MatInputModule
    1.18
    InputModule
    1.00
    ListModule
    0.96
    AnimationsModule
    0.86
    CardModule
    0.73
     BrowserModule
    0.46
    Activations Density 0.000%

    No Known Activations