© 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-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 8845
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in textual content, possibly related to formatting or punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.75
     ویکی‌پدی
    -0.62
     الدولى
    -0.55
    endwhile
    -0.55
    лтемелер
    -0.54
    Jeografia
    -0.52
    يكب
    -0.52
    thâu
    -0.52
    });*/
    -0.50
    exels
    -0.50
    POSITIVE LOGITS
    ................
    0.43
    ldots
    0.41
     kind
    0.41
     firestore
    0.39
     ...
    0.39
    OnClickListener
    0.39
     comp
    0.38
     ..........
    0.37
     Discord
    0.37
     stoff
    0.37
    Activations Density 0.162%

    No Known Activations