© 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. 37-GEMMASCOPE-RES-16K
    11. 4264
    Prev
    Next
    INDEX
    Explanations

    variations of the name "Kar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Head
    -0.40
     head
    -0.32
    Head
    -0.31
     Co
    -0.30
     Bay
    -0.29
     Short
    -0.29
     HEAD
    -0.29
     الخ
    -0.27
     room
    -0.27
     short
    -0.27
    POSITIVE LOGITS
    tanleria
    0.82
     AssemblyCulture
    0.80
    TagMode
    0.79
    parsedMessage
    0.77
    PropertyChanging
    0.72
    ReusableCell
    0.71
     linkovi
    0.70
     мәкал
    0.70
     '\\;'
    0.68
     فريبيس
    0.66
    Activations Density 0.241%

    No Known Activations