© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8311
    Prev
    Next
    INDEX
    Explanations

    references to letter "O" or its variations in different contexts

    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
    rungsseite
    -0.53
     democrática
    -0.50
     démocr
    -0.50
    LayoutPanel
    -0.48
     conducción
    -0.48
    脚注の使い方
    -0.47
     Económica
    -0.46
     kepercayaan
    -0.46
    RegressionTest
    -0.46
     Photocase
    -0.46
    POSITIVE LOGITS
    yntaxException
    0.44
     coup
    0.43
     للاسماء
    0.39
    ConfigureAwait
    0.38
    Scheme
    0.38
    SaveChangesAsync
    0.37
     numerus
    0.35
     informée
    0.35
     BS
    0.34
     Rend
    0.32
    Activations Density 0.210%

    No Known Activations