© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8954
    Prev
    Next
    INDEX
    Explanations

    terms related to efficiency and effectiveness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    openqa
    -0.80
    hasNext
    -0.75
     RUB
    -0.75
     Marston
    -0.75
     mapStateToProps
    -0.74
    FormGroup
    -0.72
     ControllerBase
    -0.72
     Chromat
    -0.70
    BlockPos
    -0.69
    bior
    -0.68
    POSITIVE LOGITS
     efficiency
    1.60
     efficient
    1.50
     efficiencies
    1.50
    efficient
    1.48
    fficiencies
    1.45
     Efficiency
    1.43
    Efficiency
    1.37
    efficiency
    1.33
     EFFICIENCY
    1.31
     Efficient
    1.31
    Activations Density 0.096%

    No Known Activations