© 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. 10754
    Prev
    Next
    INDEX
    Explanations

    different types of programming constructs and syntax elements

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

    Code syntax/delimiters

    np_acts-logits-general · gemini-2.0-flash

    HTML tags and punctuation

    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
    SourceChecksum
    -0.68
     _)
    -0.63
    səhifə
    -0.61
     tartalomajánló
    -0.58
    grine
    -0.56
    بوابة
    -0.56
    ++
    -0.56
    PyExc
    -0.55
    RTGC
    -0.55
    addContainerGap
    -0.54
    POSITIVE LOGITS
     كومونز
    0.58
     يتيمه
    0.47
    ientôt
    0.43
     للاسماء
    0.42
    verwijspagina
    0.41
     gwiazd
    0.41
     الحره
    0.40
    以及
    0.40
     valamint
    0.40
     manualidades
    0.40
    Activations Density 0.614%

    No Known Activations