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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1633
    Prev
    Next
    INDEX
    Explanations

    function definitions and user-related properties in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TargetException
    -0.49
    WireFormatLite
    -0.48
    XmlAccessType
    -0.42
     jadx
    -0.40
    isContained
    -0.38
    WriteBarrier
    -0.36
    transQ
    -0.36
    AxisAlignment
    -0.35
    ittarius
    -0.35
    Aholisi
    -0.35
    POSITIVE LOGITS
    modelBuilder
    0.50
    Chham
    0.49
    évaluateur
    0.46
     tiroirs
    0.44
    sizeCache
    0.44
    InSection
    0.41
     Designed
    0.41
     sesta
    0.41
     intStringLen
    0.41
     devoirs
    0.40
    Activations Density 0.513%

    No Known Activations