© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14911
    Prev
    Next
    INDEX
    Explanations

    Java keywords and class structures in code snippets

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

    Code, database, or technical names

    np_acts-logits-general · gemini-2.0-flash

    code and technical terms

    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
    ="@+
    -0.46
     Your
    -0.42
     though
    -0.39
    וני
    -0.39
     sch
    -0.39
     ber
    -0.37
    inck
    -0.37
    fillStyle
    -0.37
     rés
    -0.37
     [
    -0.37
    POSITIVE LOGITS
    ::
    1.20
    ItemBackground
    0.93
    ::_('
    0.88
    ControllerAdvice
    0.85
    ArrowToggle
    0.82
    featureID
    0.77
    ::__
    0.74
     ::
    0.74
     فريبيس
    0.74
    ::_
    0.69
    Activations Density 0.331%

    No Known Activations