© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9816
    Prev
    Next
    INDEX
    Explanations

    mentions of television broadcasting and related media roles

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

    television broadcasting terminology and references to sports media coverage.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
     fundas
    -0.38
    Diweddarwch
    -0.38
    Lauf
    -0.36
    lauf
    -0.35
    VIAF
    -0.35
    ➌
    -0.34
     Introduce
    -0.33
     منها
    -0.33
    řevě
    -0.33
    PENDAHULUAN
    -0.33
    POSITIVE LOGITS
    AndEndTag
    0.63
     broadcast
    0.60
     broadcasts
    0.56
    +#+
    0.53
    :+:
    0.53
    hoeddwyd
    0.52
     transmissão
    0.52
     televised
    0.52
     livestream
    0.52
    delwed
    0.52
    Activations Density 0.231%

    No Known Activations