© 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. 16-GEMMASCOPE-RES-16K
    11. 6943
    Prev
    Next
    INDEX
    Explanations

    indicators of significant entities or events in a narrative context

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

    Appears before single letters

    np_acts-logits-general · gemini-2.0-flash

    polysaccharides, supplementary, conclusion

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     متعلقه
    -0.61
    bier
    -0.59
     Malle
    -0.57
    ◀
    -0.55
    aton
    -0.55
    ary
    -0.53
    ATON
    -0.52
     Bier
    -0.52
    кет
    -0.51
    ers
    -0.49
    POSITIVE LOGITS
    ViewImports
    0.82
    aktery
    0.82
     Administrativna
    0.81
    johtaja
    0.80
    shields
    0.80
    GenerationType
    0.79
    InjectAttribute
    0.79
    EndContext
    0.79
    çalves
    0.79
    archiviato
    0.79
    Activations Density 0.409%

    No Known Activations