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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 883
    Prev
    Next
    INDEX
    Explanations

    references to features or characteristics of products or content

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

    containing "feature"

    np_acts-logits-general · gemini-2.0-flash

    describing what something has

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
     sanitario
    -0.58
     abstrato
    -0.57
     abstrait
    -0.52
     abstracto
    -0.52
     estratégico
    -0.49
     Komunikasi
    -0.49
    SharedDtor
    -0.48
     Económica
    -0.47
     techniczne
    -0.47
     publiques
    -0.47
    POSITIVE LOGITS
     feature
    1.81
     Feature
    1.70
    feature
    1.65
     featured
    1.54
     features
    1.54
     FEATURE
    1.53
    Feature
    1.52
    features
    1.45
     Features
    1.39
    FEATURE
    1.38
    Activations Density 0.075%

    No Known Activations