© 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. 58907
    Prev
    Next
    INDEX
    Explanations

    ingredients used in healthy cooking, particularly plant-based seeds and oils

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

    seeds and their extracts

    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
    ੝
    -0.58
     rhestr
    -0.58
     ujednoznacz
    -0.57
    
    -0.57
     Geſch
    -0.55
     dieſem
    -0.54
     ſchon
    -0.53
     utafitiHapana
    -0.53
     deſſen
    -0.53
    celotti
    -0.53
    POSITIVE LOGITS
     seeds
    0.68
     seed
    0.68
     SEED
    0.66
    seed
    0.65
     sesame
    0.59
     semillas
    0.59
     Seed
    0.58
    Seed
    0.56
    SEED
    0.56
     Seeds
    0.54
    Activations Density 0.010%

    No Known Activations