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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 45431
    Prev
    Next
    INDEX
    Explanations

    references to social gatherings and events

    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
    UnknownFields
    -0.51
     ivelany
    -0.47
    EntryPoint
    -0.43
    FDRE
    -0.40
     podjela
    -0.40
    ško
    -0.40
    </thead>
    -0.38
    Japon
    -0.38
    czer
    -0.38
    ONES
    -0.38
    POSITIVE LOGITS
     event
    0.63
     evento
    0.59
     party
    0.59
     wedding
    0.55
     events
    0.52
     festa
    0.52
     eventos
    0.51
     evenement
    0.49
     Veranstaltung
    0.48
    AutoScaleMode
    0.48
    Activations Density 0.011%

    No Known Activations