Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4808
    Prev
    Next
    INDEX
    Explanations

    words related to scientific and medical fields, particularly focusing on terminology associated with studies, procedures, and properties

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

    ending with "st" or similar sounds

    np_acts-logits-general · gemini-2.0-flash

    words ending in ast, ost, ist

    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
    клопе
    -0.97
     الدولى
    -0.95
    rrggbb
    -0.94
     Duggan
    -0.93
    Rohy
    -0.91
     Meksiku
    -0.88
    aarrggbb
    -0.86
    IsMutable
    -0.85
    нодоро
    -0.83
    ukone
    -0.83
    POSITIVE LOGITS
    bst
    0.73
    ast
    0.72
    AST
    0.71
     Bist
    0.71
    BAST
    0.69
    ost
    0.69
     Rast
    0.68
    OST
    0.67
     OST
    0.67
     Ost
    0.66
    Activations Density 0.664%

    No Known Activations