Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3574
    Prev
    Next
    INDEX
    Explanations

    product specifications related to eyewear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     capa
    -0.38
    setViewportView
    -0.32
    loj
    -0.31
    unda
    -0.30
    ありますが
    -0.30
     cra
    -0.30
    dot
    -0.30
     تواند
    -0.30
     INA
    -0.29
    fran
    -0.29
    POSITIVE LOGITS
     kasarigan
    0.64
     FetchType
    0.60
     transfieras
    0.59
    IVEREF
    0.54
     themſelves
    0.52
    contentLoaded
    0.51
     OMITBAD
    0.51
    verwijspagina
    0.50
    はじめに
    0.49
    astéroïdes
    0.48
    Activations Density 0.297%

    No Known Activations