© 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. 38-GEMMASCOPE-RES-16K
    11. 15799
    Prev
    Next
    INDEX
    Explanations

    frequent occurrences of punctuation and related structural elements in text

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

    punctuation marks that separate clauses or sentences, particularly semicolons and periods.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.59
    ItemBackground
    -0.45
    Rüyada
    -0.41
    parsedMessage
    -0.36
    Morfologia
    -0.35
    Хьажоргаш
    -0.34
     ***!
    -0.33
    ובי
    -0.33
     mà
    -0.32
    Források
    -0.32
    POSITIVE LOGITS
     however
    3.55
    however
    2.78
     However
    2.75
    However
    2.66
     entanto
    2.63
     однако
    2.48
     però
    2.45
     tuttavia
    2.45
     cependant
    2.39
     jedoch
    2.34
    Activations Density 1.131%

    No Known Activations