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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 799
    Prev
    Next
    INDEX
    Explanations

    transitive verbs and their objects indicating actions involving interaction or movement

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

    Following questions or uncertainty

    np_acts-logits-general · gemini-2.0-flash

    explaining circumstances or reasons

    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
     judiciaire
    -0.48
     acompañar
    -0.47
     wśród
    -0.45
     demás
    -0.45
    árbol
    -0.45
     desmotivaciones
    -0.44
    fotografía
    -0.44
     dramatique
    -0.43
     láp
    -0.43
     contrário
    -0.43
    POSITIVE LOGITS
     Waray
    0.57
    izr
    0.56
    +#+#
    0.50
    oneph
    0.50
    grine
    0.49
    wpi
    0.49
    usse
    0.47
    guin
    0.47
     AssemblyVersion
    0.47
    UserScript
    0.46
    Activations Density 0.411%

    No Known Activations