© 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. 4756
    Prev
    Next
    INDEX
    Explanations

    references to various people, their achievements, and relationships within a context involving details about media and entertainment

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

    "See also", "Names", "Places", or similar section titles

    np_acts-logits-general · gemini-2.0-flash

    miscellaneous

    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
     становника
    -0.71
     estekak
    -0.63
    ConstraintMaker
    -0.59
    SourceChecksum
    -0.58
     forskj
    -0.53
     acela
    -0.53
    AdapterFactory
    -0.52
     econômica
    -0.52
     byen
    -0.52
     recensement
    -0.52
    POSITIVE LOGITS
     miscellaneous
    0.81
     misc
    0.75
    以下是
    0.66
    cellaneous
    0.66
    あとは
    0.66
     Misc
    0.65
    その他
    0.61
    Others
    0.61
     other
    0.60
     Miscellaneous
    0.60
    Activations Density 0.222%

    No Known Activations