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. 22-GEMMASCOPE-RES-16K
    6. 14020
    Prev
    Next
    INDEX
    Explanations

    HTML tags and elements related to formatting and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forKey
    -0.50
     задача
    -0.49
    ranton
    -0.48
     argc
    -0.46
    หวัด
    -0.46
    obacterium
    -0.45
    jsonwebtoken
    -0.45
    GraphicsUnit
    -0.44
    niosek
    -0.43
    @[
    -0.42
    POSITIVE LOGITS
     style
    3.76
     Style
    3.39
    style
    3.34
    Style
    3.21
     STYLE
    3.06
    STYLE
    2.77
     styles
    2.73
     estilo
    2.62
     Styles
    2.42
     stile
    2.29
    Activations Density 0.107%

    No Known Activations