© 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. 30-GEMMASCOPE-RES-16K
    11. 10874
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements in programming

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

    before or after dashes

    np_acts-logits-general · gemini-2.0-flash

    molecular compounds, plaintiff sustained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.79
     otomatig
    -0.62
    Portale
    -0.62
     صوتيه
    -0.60
    
    -0.52
    rungsseite
    -0.52
    abestanden
    -0.51
     Chwiliwch
    -0.51
    argout
    -0.50
     disambiguazione
    -0.50
    POSITIVE LOGITS
     deſt
    0.34
    Nowhere
    0.33
     الرياضيه
    0.32
    jší
    0.32
     مك
    0.32
    madd
    0.31
    ſelves
    0.31
    intéress
    0.31
    VIRON
    0.31
     Nowhere
    0.30
    Activations Density 0.234%

    No Known Activations