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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1050
    Prev
    Next
    INDEX
    Explanations

    topics related to housing, health services, and credit opportunities

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

    keywords related to literacy, regulatory frameworks, and housing issues

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

    housing acts and initiatives

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
      (
    -0.56
    ImageField
    -0.55
     Carrasco
    -0.54
    liffe
    -0.52
    tedly
    -0.51
     userSchema
    -0.50
    hängt
    -0.50
    らかに
    -0.50
    èdia
    -0.50
     bolas
    -0.49
    POSITIVE LOGITS
    LookAnd
    0.71
     Inti
    0.63
    IVEREF
    0.60
     виправивши
    0.56
    exitRule
    0.55
     Италијани
    0.55
    IndentedString
    0.54
    reactstrap
    0.54
     Bauhaus
    0.53
    CreateMap
    0.53
    Activations Density 0.134%

    No Known Activations