© 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. 11864
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to legal and procedural contexts

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

    followed by punctuation or numbers

    np_acts-logits-general · gemini-2.0-flash

    end of sentence or question

    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
     שוליים
    -0.96
     للمعارف
    -0.92
    >\<^
    -0.82
    GenerationType
    -0.82
     LoggerFactory
    -0.82
     مرئيه
    -0.82
    astéroïdes
    -0.81
    
    -0.81
    GHIJKLM
    -0.81
    /−
    -0.80
    POSITIVE LOGITS
    ?
    0.96
    ↵
    0.95
    ?"
    0.90
    !
    0.80
    ")
    0.77
    ");
    0.76
    ↵↵
    0.76
    ?”
    0.76
    ??
    0.74
    </h2>
    0.74
    Activations Density 4.913%

    No Known Activations