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. 80796
    Prev
    Next
    INDEX
    Explanations

    references to annual events and gatherings

    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
    velser
    -0.38
    .*")]
    -0.38
    MigrationBuilder
    -0.36
     køb
    -0.34
    calça
    -0.34
     arquitetura
    -0.34
    })]
    -0.34
     structural
    -0.34
     empty
    -0.34
    談社
    -0.34
    POSITIVE LOGITS
     anual
    0.65
    annual
    0.63
     annual
    0.57
     yearly
    0.57
    Annual
    0.56
     annually
    0.56
    ANNUAL
    0.53
     ANNUAL
    0.52
     Annual
    0.50
    yearly
    0.50
    Activations Density 0.012%

    No Known Activations