© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 12882
    Prev
    Next
    INDEX
    Explanations

    keywords related to user interface elements and interactions

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

    action words or commands

    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
    PYX
    -0.54
    ⟬
    -0.47
    KommentareTeilen
    -0.46
     lizenzfreie
    -0.40
    PyExc
    -0.38
    #
    -0.38
    QMetaType
    -0.38
    তথ্যসূত্র
    -0.37
    VersionUID
    -0.36
     createSprite
    -0.36
    POSITIVE LOGITS
     considérons
    0.48
    LabelTagHelper
    0.47
    $_['
    0.47
     mahd
    0.45
    cdnjs
    0.45
    numerusform
    0.44
     registered
    0.42
    InstrumentedTest
    0.42
    imageshack
    0.41
     autorytatywna
    0.40
    Activations Density 0.001%

    No Known Activations