© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13738
    Prev
    Next
    INDEX
    Explanations

    information about the invention and origins of specific food items

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

    Date or location following "invented" or similar words

    np_acts-logits-general · gemini-2.0-flash

    invented and developed

    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
     '\\;'
    -0.62
    ConstraintMaker
    -0.60
    IntoConstraints
    -0.59
    RotationOrder
    -0.59
    featureID
    -0.59
     queſta
    -0.59
    AddTagHelper
    -0.59
     CURIAM
    -0.59
     CreateTagHelper
    -0.58
    Personensuche
    -0.57
    POSITIVE LOGITS
     invented
    0.68
     originated
    0.52
     придума
    0.52
     dikembangkan
    0.48
     invention
    0.43
     developed
    0.42
     introduced
    0.42
    が発
    0.42
     inspired
    0.41
     pioneered
    0.40
    Activations Density 0.713%

    No Known Activations