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. 10773
    Prev
    Next
    INDEX
    Explanations

    references to teams and collaborative groups, particularly in research and medical contexts

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

    Group or team composition

    np_acts-logits-general · gemini-2.0-flash

    teams, groups, and their members

    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
    出版年
    -0.71
    enumi
    -0.70
    awtextra
    -0.63
    AndEndTag
    -0.61
    batore
    -0.61
    figer
    -0.57
    '}>
    -0.57
    AddTagHelper
    -0.56
    ()]
    
    -0.54
    ceuticals
    -0.54
    POSITIVE LOGITS
     members
    1.24
     consisting
    1.22
     composed
    1.13
     comprising
    1.12
     comprised
    1.09
     consists
    1.04
     consisted
    1.04
     terdiri
    1.03
    members
    0.98
     composto
    0.96
    Activations Density 0.445%

    No Known Activations