© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11254
    Prev
    Next
    INDEX
    Explanations

    names of symphony orchestras and musical institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Orchestras or musical ensembles

    np_acts-logits-general · gemini-2.0-flash

    orchestras and bands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnitTesting
    -0.66
    awtextra
    -0.63
    KEYCODE
    -0.60
    ništ
    -0.57
     Lyrics
    -0.54
     muualla
    -0.54
    Lyrics
    -0.53
     lyrics
    -0.52
    ebilir
    -0.52
     ujednoznacz
    -0.52
    POSITIVE LOGITS
     band
    1.24
     bands
    0.99
    band
    0.95
     Band
    0.95
     ensemble
    0.82
     BAND
    0.80
     quartet
    0.78
     orchestra
    0.78
    Band
    0.77
     banda
    0.71
    Activations Density 0.118%

    No Known Activations