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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 797
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or help

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

    Requests for help or assistance

    np_acts-logits-general · gemini-2.0-flash

    requests for help or assistance

    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-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
     Metzger
    -0.44
     kyse
    -0.42
     Wachs
    -0.40
     sequência
    -0.38
    RetentionPolicy
    -0.38
    newtheorem
    -0.37
     Kraus
    -0.37
    slidesToShow
    -0.37
     asamblea
    -0.37
     absolutely
    -0.36
    POSITIVE LOGITS
    help
    1.23
    Help
    1.15
     Help
    1.15
     assistance
    1.11
     Assistance
    1.10
    assistance
    1.08
     Helper
    1.08
     help
    1.06
    HELP
    1.06
     Aid
    1.05
    Activations Density 0.186%

    No Known Activations