© 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 EvalsExportsAPI 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. 14789
    Prev
    Next
    INDEX
    Explanations

    arguments involving denial and accountability

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

    Tokens preceding "user" or related to a new turn

    np_acts-logits-general · gemini-2.0-flash

    user input after turn start

    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
     createSprite
    -0.53
     متعلقه
    -0.43
    cydow
    -0.40
    uestamente
    -0.39
     locaux
    -0.39
     galax
    -0.39
    Extr
    -0.38
    synchron
    -0.38
     chrétiens
    -0.38
    ennom
    -0.37
    POSITIVE LOGITS
    Vidite
    0.59
    TRAILING
    0.47
    sizeCache
    0.47
    Sucesor
    0.46
     embarrassed
    0.44
    GEBURTSDATUM
    0.44
    PostInfinity
    0.43
    parsedMessage
    0.42
    KommentareTeilen
    0.42
     embarrassing
    0.40
    Activations Density 0.352%

    No Known Activations