© 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. 41-GEMMASCOPE-RES-16K
    11. 7671
    Prev
    Next
    INDEX
    Explanations

    topics related to socio-economic commentary and racial considerations in admissions processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelSerializer
    -0.54
    BagConstraints
    -0.52
     propOrder
    -0.47
     дописавши
    -0.46
    MigrationBuilder
    -0.44
     restTemplate
    -0.43
     referenties
    -0.41
     JpaRepository
    -0.38
     lenker
    -0.38
    IntoConstraints
    -0.37
    POSITIVE LOGITS
     management
    1.05
     creation
    1.02
     development
    0.95
    creation
    0.93
     formation
    0.89
     production
    0.87
     maintenance
    0.86
     acquisition
    0.84
     promotion
    0.84
     preparation
    0.81
    Activations Density 1.122%

    No Known Activations