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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 99537
    Prev
    Next
    INDEX
    Explanations

    phrases and terms that refer to a sequence or connection of elements

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

    chain structures or sequences

    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
     כן
    -0.46
    .');
    -0.43
    TargetException
    -0.40
     PPD
    -0.40
    addGap
    -0.40
    しくは
    -0.39
    terscotch
    -0.39
     Vicky
    -0.39
    .");
    -0.38
     Novo
    -0.38
    POSITIVE LOGITS
     chain
    1.27
    Chain
    1.27
     Chain
    1.23
    chain
    1.22
     CHAIN
    1.18
    CHAIN
    1.10
     chains
    1.05
    chains
    0.99
    Chains
    0.95
     Chains
    0.94
    Activations Density 0.008%

    No Known Activations