© 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. 7987
    Prev
    Next
    INDEX
    Explanations

    references to specific groups or classifications, particularly in various contexts such as companies, technology, and social issues

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

    followed by a comma or "are"

    np_acts-logits-general · gemini-2.0-flash

    some X

    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
    MigrationBuilder
    -1.02
    Datuak
    -0.68
    DoubleQuotes
    -0.66
    Билгалдахарш
    -0.66
     externi
    -0.65
     linkovi
    -0.63
     OFDb
    -0.63
    ibatis
    -0.62
    AndEndTag
    -0.60
     oprot
    -0.60
    POSITIVE LOGITS
     even
    0.83
     sogar
    0.71
     addirittura
    0.70
     may
    0.65
     zelfs
    0.65
     bahkan
    0.64
    甚至
    0.64
    甚至是
    0.62
     simply
    0.61
     Even
    0.59
    Activations Density 0.293%

    No Known Activations