© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 14241
    Prev
    Next
    INDEX
    Explanations

    the recurring concept of "minimal" and "minimum" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.66
    
    -0.57
    ImageContext
    -0.55
    octanol
    -0.50
    cheduler
    -0.50
     NSCoder
    -0.49
    KommentareTeilen
    -0.47
    findpost
    -0.47
    enumii
    -0.47
    ScreenState
    -0.47
    POSITIVE LOGITS
     minimal
    2.84
    minimal
    2.55
     Minimal
    2.50
    Minimal
    2.50
     minimum
    2.31
     Minimum
    2.05
     минима
    2.05
     minimale
    2.03
    minimum
    2.03
    Minimum
    1.96
    Activations Density 0.237%

    No Known Activations