© 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 EvalsExportsinterp-engineNEWAPI 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. 67183
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "deux" and its variations, indicating a focus on the concept of "two"

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

    counting two items

    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
     Landschaft
    -0.50
     caminhada
    -0.48
    mathcal
    -0.48
    PullParser
    -0.46
     Anleitung
    -0.45
    zzleHttp
    -0.45
    baliknya
    -0.44
    การณ์
    -0.43
     beraber
    -0.43
     jaką
    -0.43
    POSITIVE LOGITS
     two
    1.04
     TWO
    0.96
     Two
    0.92
    Two
    0.87
    two
    0.84
     zwei
    0.84
     Два
    0.82
     два
    0.81
    Два
    0.81
    TWO
    0.81
    Activations Density 0.001%

    No Known Activations