© 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. 49905
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize revolution, struggle, and determination in a political context

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

    describing states or outcomes

    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
    tagHelperRunner
    -0.63
    håll
    -0.55
    Hentet
    -0.52
    Życiorys
    -0.52
    +:+
    -0.52
     surla
    -0.52
    +#+#
    -0.52
    jsxFileName
    -0.49
    AddTagHelper
    -0.48
     ProtoMessage
    -0.48
    POSITIVE LOGITS
    CloseOperation
    0.42
    resizingMask
    0.39
     quæ
    0.35
    ConstraintLayout
    0.35
    RefNanny
    0.35
    SuspendLayout
    0.34
    layoutControl
    0.34
    ◆◆
    0.34
     final
    0.34
     IndexPath
    0.34
    Activations Density 0.034%

    No Known Activations