© 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28248
    Prev
    Next
    INDEX
    Explanations

    instances of the term "etc." indicating an incomplete list or additional examples

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

    lists and et cetera

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kammer
    -0.68
     Gree
    -0.65
    oem
    -0.61
     KAM
    -0.61
    Von
    -0.61
    DNEY
    -0.60
    Nonnull
    -0.59
     Gallen
    -0.59
    oval
    -0.59
    uuid
    -0.59
    POSITIVE LOGITS
    etera
    1.56
    etc
    0.97
     ETC
    0.96
    ETC
    0.95
     etc
    0.91
    Etc
    0.89
    ništ
    0.87
     Etc
    0.85
    曖昧さ回避
    0.79
     дописавши
    0.78
    Activations Density 0.022%

    No Known Activations