© 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. 3-GEMMASCOPE-RES-16K
    11. 4880
    Prev
    Next
    INDEX
    Explanations

    references to the act of scratching and related tools or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.48
    SharedDtor
    -0.48
     bosom
    -0.47
     Biôgrafia
    -0.44
     estekak
    -0.44
    boldmath
    -0.43
    ніципалі
    -0.42
     OMITBAD
    -0.40
     opie
    -0.39
     Edel
    -0.39
    POSITIVE LOGITS
     scratch
    0.91
    scrap
    0.91
     clause
    0.85
     Bureau
    0.82
    Scrap
    0.81
     scrap
    0.81
     Scra
    0.79
     Scrap
    0.79
     scrapped
    0.79
     knife
    0.78
    Activations Density 0.142%

    No Known Activations