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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120132
    Prev
    Next
    INDEX
    Explanations

    financial terms related to utility and maintenance expenses

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

    utilities and taxes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    StoryboardSegue
    -0.54
    pias
    -0.46
    hynchus
    -0.45
    ciela
    -0.45
    Cormack
    -0.44
    brecht
    -0.44
    entyfik
    -0.44
    odora
    -0.44
    spread
    -0.43
     Maxime
    -0.43
    POSITIVE LOGITS
    BagConstraints
    0.41
     AssemblyCompany
    0.40
     manutenzione
    0.40
     policial
    0.40
     <<<<<<<<<<<<<<
    0.40
    awtextra
    0.39
    Portály
    0.38
     mensuales
    0.38
     excepción
    0.36
     coût
    0.36
    Activations Density 0.002%

    No Known Activations