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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 4956
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of people and places

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

    Preceding date or days of the week

    np_acts-logits-general · gemini-2.0-flash

    Saturday, Sunday, Committee, employee, firm, parents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }}$,
    -1.04
     []),
    -0.92
    .},
    -0.92
     ''),
    -0.86
     ""),
    -0.83
     {}),
    -0.78
    ')}}"
    -0.75
    Lähteet
    -0.75
    zaamheid
    -0.75
    */,
    -0.75
    POSITIVE LOGITS
    ,
    1.87
    、
    0.72
    ،
    0.55
    ,_
    0.50
    ,
    0.47
    ituary
    0.43
    ‚
    0.42
    ・
    0.40
     الاطلاع
    0.40
    ImageContext
    0.38
    Activations Density 0.753%

    No Known Activations