© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4618
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to sharpness and precision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "sharp" and sharpness

    np_acts-logits-general · gemini-2.0-flash

    quality of sharp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
     tub
    -0.39
    postIndex
    -0.39
    AnchorTagHelper
    -0.39
    verwijspagina
    -0.39
     Cab
    -0.39
    __(/*!
    -0.38
     union
    -0.38
    KURZBESCHREIBUNG
    -0.36
    vinfos
    -0.36
    ">...
    -0.36
    POSITIVE LOGITS
     sharp
    1.98
    sharp
    1.85
     Sharp
    1.83
    Sharp
    1.80
     sharper
    1.71
     SHARP
    1.69
     sharpness
    1.61
     sharpen
    1.52
     tajam
    1.42
     sharpened
    1.40
    Activations Density 0.160%

    No Known Activations