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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 305
    Prev
    Next
    INDEX
    Explanations

    semicolons in the text

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

    punctuation, specifically semicolons

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

    code loops and ATP

    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
    <bos>
    -0.47
    StructEnd
    -0.44
    (__('
    -0.43
    Skocz
    -0.41
    MLLoader
    -0.40
     setEmail
    -0.39
    је
    -0.39
    Pick
    -0.39
    InputBorder
    -0.39
    dateTimePicker
    -0.39
    POSITIVE LOGITS
    ftagPool
    0.84
    AndEndTag
    0.83
     &___
    0.77
    toarele
    0.75
    ngdoc
    0.75
    nodoc
    0.75
    Personendaten
    0.74
    IContainer
    0.73
    Referències
    0.73
    +#+#
    0.72
    Activations Density 0.003%

    No Known Activations