© 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. 39-GEMMASCOPE-RES-16K
    11. 2488
    Prev
    Next
    INDEX
    Explanations

    programming-related elements and error handling keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/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.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.70
    ")==
    -0.65
    ьаж
    -0.57
    ']==
    -0.54
    WireFormatLite
    -0.54
     dearth
    -0.53
    xase
    -0.51
    Lack
    -0.50
    AccessorTable
    -0.50
    ParallelGroup
    -0.49
    POSITIVE LOGITS
     !=
    1.23
    !=
    0.79
     ≠
    0.73
     не
    0.72
     wasn
    0.68
    ()!=
    0.68
    ≠
    0.68
    ]!=
    0.66
    )!=
    0.65
     khác
    0.63
    Activations Density 0.314%

    No Known Activations