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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 15703
    Prev
    Next
    INDEX
    Explanations

    multiple forms of writing, storytelling, and creative expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     judiciaire
    -0.39
     Pantalla
    -0.38
    CloseOperation
    -0.36
     Jurí
    -0.36
     pemerintah
    -0.35
     civili
    -0.35
     informée
    -0.35
     kön
    -0.34
     poderão
    -0.34
     démocratique
    -0.34
    POSITIVE LOGITS
    AccessorTable
    0.60
     sketchbook
    0.59
     brainstorm
    0.59
     sketched
    0.59
     ideas
    0.59
     sketches
    0.58
     sketch
    0.54
     brainstorming
    0.50
     giddy
    0.47
     tinkering
    0.47
    Activations Density 0.270%

    No Known Activations