© 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. 37-GEMMASCOPE-RES-16K
    6. 4792
    Prev
    Next
    INDEX
    Explanations

    Python code syntax and function calls related to the operating system module

    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
     AssemblyCulture
    -0.57
     houſe
    -0.53
     pleaſure
    -0.52
    AISSEE
    -0.50
    Personensuche
    -0.47
    unlimited
    -0.47
     fubject
    -0.47
    myModal
    -0.47
    disposing
    -0.46
    enterOuterAlt
    -0.46
    POSITIVE LOGITS
    sep
    0.40
     séparation
    0.35
     separación
    0.35
    ']):
    0.34
     táctil
    0.33
    Nor
    0.33
    ɵɵelementEnd
    0.33
    ล
    0.32
    ))));
    0.32
     access
    0.32
    Activations Density 0.284%

    No Known Activations