© 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. 31-GEMMASCOPE-RES-16K
    11. 3438
    Prev
    Next
    INDEX
    Explanations

    programming language syntax constructs and methods related to file handling and error reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing operations on file handles and database connections.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glGen
    -0.44
     CURLOPT
    -0.39
     configureStore
    -0.39
    glLoad
    -0.38
    InjectMocks
    -0.37
     vej
    -0.36
    neux
    -0.36
     Siri
    -0.35
    offsetof
    -0.34
     introduction
    -0.34
    POSITIVE LOGITS
     closing
    1.03
     closes
    0.98
     Closing
    0.91
    close
    0.89
     Closes
    0.88
     cleanup
    0.87
    closing
    0.87
     closed
    0.86
    关闭
    0.85
     Cleanup
    0.85
    Activations Density 0.302%

    No Known Activations