© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 96767
    Prev
    Next
    INDEX
    Explanations

    discussions about labor rights and inequities

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

    negation or qualification followed by statement

    np_acts-logits-general · gemini-2.5-flash-lite

    statements that argue a minimizing or defensive stance—denials, euphemisms, or justifications—especially in quoted or legalistic argumentative phrasing about contested harms.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    GraphicsUnit
    -0.36
     CreateTagHelper
    -0.35
    AnchorStyles
    -0.34
    LOGIC
    -0.34
     RY
    -0.32
    Geografi
    -0.32
     vis
    -0.32
    tter
    -0.32
     Estr
    -0.31
     ويكيپيديا
    -0.31
    POSITIVE LOGITS
    verwijspagina
    0.56
     חיצוניים
    0.52
    StoryboardSegue
    0.48
    bens
    0.46
     HasFactory
    0.46
     ApiException
    0.45
     podjela
    0.45
     nonUne
    0.45
    Билгалдахарш
    0.45
     متعلقه
    0.45
    Activations Density 0.159%

    No Known Activations