© 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. 38-GEMMASCOPE-RES-16K
    11. 13591
    Prev
    Next
    INDEX
    Explanations

    code block structures or opening braces in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.63
     &___
    -0.62
    RTLI
    -0.59
     typelib
    -0.56
     незавершена
    -0.54
     لينك
    -0.54
     useAppContext
    -0.53
     ſte
    -0.52
     ſind
    -0.51
    "}")
    -0.51
    POSITIVE LOGITS
       
    0.44
    ComponentModel
    0.36
    chließend
    0.35
    capaian
    0.34
    erdings
    0.34
     Freundin
    0.32
    циона
    0.32
    omaly
    0.32
    которые
    0.32
     initComponents
    0.32
    Activations Density 0.083%

    No Known Activations