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. 3155
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical group theory and properties of groups

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

    Finitely generated groups

    np_acts-logits-general · gemini-2.0-flash

    finitely generated virtually nilpotent groups

    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
     unknownFields
    -0.58
    LEncoder
    -0.53
    XmlAccessType
    -0.52
    WebControls
    -0.49
     válida
    -0.47
     Coul
    -0.46
     Chall
    -0.44
     concor
    -0.43
    %;">
    -0.43
    ysacchar
    -0.42
    POSITIVE LOGITS
     subgroup
    0.83
     subgroups
    0.78
     getGroup
    0.77
     group
    0.74
    ftagPool
    0.73
    الحياه
    0.73
    djangoproject
    0.71
     groups
    0.70
    group
    0.67
    GroupName
    0.66
    Activations Density 1.286%

    No Known Activations