© 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. 38-GEMMASCOPE-RES-16K
    11. 7905
    Prev
    Next
    INDEX
    Explanations

    directives and commands related to compliance and behavior

    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
    matchCondition
    -0.48
    Referencoj
    -0.44
    cotch
    -0.44
     beroep
    -0.43
     хочется
    -0.43
    endpush
    -0.42
     enjoying
    -0.40
     الحره
    -0.40
    makeText
    -0.40
     scoprire
    -0.39
    POSITIVE LOGITS
     reconsider
    0.75
     möge
    0.68
     desist
    0.66
     cooperate
    0.63
     vacate
    0.60
     join
    0.59
     cease
    0.57
     cesse
    0.56
     participate
    0.54
     stop
    0.53
    Activations Density 0.610%

    No Known Activations