Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1811
    Prev
    Next
    INDEX
    Explanations

    components of coding syntax and structure in programming languages

    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
    __
    -0.35
     Kimball
    -0.34
    tablir
    -0.34
    bemos
    -0.32
     continuación
    -0.31
     Kapelle
    -0.31
    return
    -0.30
    Factory
    -0.30
     return
    -0.29
    ro
    -0.29
    POSITIVE LOGITS
     autorytatywna
    1.02
    httphttps
    0.97
    تقاوى
    0.93
    mobileqq
    0.90
     Италијани
    0.88
    ThroughAttribute
    0.84
    jsxFileName
    0.82
     localObject
    0.82
    +#+#
    0.82
    webElementXpaths
    0.81
    Activations Density 0.239%

    No Known Activations