© 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. 16-GEMMASCOPE-RES-16K
    11. 11771
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and comments within code snippets

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

    Code snippets and markup

    np_acts-logits-general · gemini-2.0-flash

    code annotations 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 @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JsonInclude
    -0.62
     BufferedWriter
    -0.54
    出版年
    -0.53
     dépos
    -0.52
    transQ
    -0.49
    sizeCache
    -0.48
     rând
    -0.46
    ⓧ
    -0.43
    oa̍t
    -0.42
    锈钢
    -0.42
    POSITIVE LOGITS
     Signalez
    0.88
    Portale
    0.78
     الحره
    0.77
    Autoritní
    0.71
    jspx
    0.65
    TagMode
    0.64
     للاسماء
    0.62
    nestjs
    0.58
    SizeMode
    0.58
    gonic
    0.57
    Activations Density 0.025%

    No Known Activations