© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 2226
    Prev
    Next
    INDEX
    Explanations

    references to committees and their structure within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fl
    -0.70
    mals
    -0.66
     Scal
    -0.66
    солю
    -0.64
    scal
    -0.63
     x
    -0.63
    yaz
    -0.62
    fro
    -0.62
     Wint
    -0.60
    :”
    -0.60
    POSITIVE LOGITS
     committees
    1.72
     Committees
    1.66
     Committee
    1.62
     committee
    1.53
     COMMITTEE
    1.48
    Committee
    1.44
    committees
    1.40
    committee
    1.39
     subcommittee
    1.14
     comité
    1.06
    Activations Density 0.038%

    No Known Activations