© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 6738
    Prev
    Next
    INDEX
    Explanations

    special characters, symbols, and specific formatting within a programming context

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

    mathematical or logical operations represented by symbols and numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    argout
    -0.58
    aarrggbb
    -0.57
    mybatisplus
    -0.53
    addCriterion
    -0.53
    queryInterface
    -0.52
    jsonwebtoken
    -0.52
    Бахар
    -0.52
    AnimationsModule
    -0.52
    ComponentModel
    -0.52
    HideFlags
    -0.51
    POSITIVE LOGITS
     line
    0.75
     Line
    0.69
    :✨
    0.67
     "..\..\..\
    0.66
     "..\..\
    0.65
     Zeile
    0.64
    setLine
    0.64
     مشين
    0.62
     lines
    0.61
     LINE
    0.61
    Activations Density 0.551%

    No Known Activations