© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 6407
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements in programming languages

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

    "set" in code or text

    np_acts-logits-general · gemini-2.0-flash

    set and change methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.36
     مشين
    -0.34
    TintMode
    -0.33
    FieldOffsetTable
    -0.32
     Allociné
    -0.31
     चीज़ों
    -0.31
    ‌پدی
    -0.30
    เอง
    -0.30
     []:
    -0.30
    fycat
    -0.30
    POSITIVE LOGITS
     set
    0.74
     Set
    0.65
    set
    0.57
    Set
    0.56
     SET
    0.52
     Plaid
    0.52
     sett
    0.51
     CURLOPT
    0.50
    gjenge
    0.50
     setters
    0.49
    Activations Density 0.135%

    No Known Activations