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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 91515
    Prev
    Next
    INDEX
    Explanations

    specific dates or days of the week

    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
     çanta
    -0.50
    utilisons
    -0.49
    OGND
    -0.49
    parsedMessage
    -0.48
    poz
    -0.48
     miniaturka
    -0.47
    øb
    -0.47
    Únete
    -0.47
    SEGUIR
    -0.47
    cfm
    -0.46
    POSITIVE LOGITS
     Friday
    0.53
     Sunday
    0.47
     morning
    0.47
     Wednesday
    0.45
     FRIDAY
    0.44
     Thursday
    0.42
     Saturday
    0.42
    DockStyle
    0.42
    morning
    0.41
     THURSDAY
    0.41
    Activations Density 0.000%

    No Known Activations