© 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. 15032
    Prev
    Next
    INDEX
    Explanations

    punctuation and various symbols used in text

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

    passages containing concrete examples, statistics, case studies, or substantive narratives with specific details.

    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
     myſelf
    -0.62
     ſta
    -0.59
     indígen
    -0.59
     miniaturka
    -0.56
     Perſ
    -0.56
     estadounid
    -0.54
    ArgsConstructor
    -0.54
     Reſ
    -0.54
    pulseira
    -0.52
     hırka
    -0.51
    POSITIVE LOGITS
     However
    0.56
     Also
    0.54
     Others
    0.54
     Their
    0.54
     Finally
    0.53
     They
    0.51
     Lastly
    0.50
     Similarly
    0.50
     Meanwhile
    0.50
     Those
    0.49
    Activations Density 1.307%

    No Known Activations