© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 9845
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sharp" as well as related descriptors or comparative terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Doria
    -0.76
     تانيه
    -0.75
    otoro
    -0.72
     дописавши
    -0.69
    AnchorTagHelper
    -0.65
    ειτουργ
    -0.65
     onOptions
    -0.65
    schild
    -0.64
    RegistryLite
    -0.63
    viale
    -0.62
    POSITIVE LOGITS
     sharp
    2.94
    sharp
    2.60
     Sharp
    2.55
    Sharp
    2.44
     SHARP
    2.33
     sharper
    2.21
     sharpness
    2.09
     sharply
    1.97
     tajam
    1.74
     sharpen
    1.71
    Activations Density 0.066%

    No Known Activations