© 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. 19-GEMMASCOPE-RES-16K
    11. 3704
    Prev
    Next
    INDEX
    Explanations

    textual patterns and formatting elements typical in coding or structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     not
    -0.63
     saja
    -0.58
     sure
    -0.54
     ही
    -0.53
    ствен
    -0.53
     же
    -0.53
     bad
    -0.53
    hetic
    -0.52
     si
    -0.50
     Dit
    -0.50
    POSITIVE LOGITS
     تانيه
    0.80
     ujednoznacz
    0.73
     nakalista
    0.69
    ArgsConstructor
    0.68
    Filmographie
    0.67
     الرياضيه
    0.64
    ipedi
    0.64
     utafitiHapana
    0.63
    mybatisplus
    0.63
     linkovi
    0.62
    Activations Density 0.049%

    No Known Activations