© 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. 9-GEMMASCOPE-RES-16K
    11. 8716
    Prev
    Next
    INDEX
    Explanations

    references to sharpness or cutting qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 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
    verwijspagina
    -0.47
     tub
    -0.47
    vinfos
    -0.47
    postIndex
    -0.47
     Cab
    -0.45
    fanfic
    -0.43
    LLocation
    -0.43
     union
    -0.42
     Erb
    -0.42
     Anch
    -0.42
    POSITIVE LOGITS
     sharp
    1.91
     Sharp
    1.74
    sharp
    1.73
    Sharp
    1.70
     sharper
    1.60
     SHARP
    1.59
     sharpness
    1.55
     tajam
    1.43
     sharpen
    1.38
     sharply
    1.31
    Activations Density 0.197%

    No Known Activations