© 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. 9-GEMMASCOPE-RES-131K
    11. 76200
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "much."

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

    much followed by adjectives or of phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     paraly
    -0.45
    Parame
    -0.44
    dois
    -0.42
    serial
    -0.42
    Autos
    -0.40
    ✎
    -0.40
    밥
    -0.40
    hardware
    -0.40
     privatisation
    -0.40
    dnd
    -0.39
    POSITIVE LOGITS
     much
    0.78
     many
    0.75
    Beaucoup
    0.70
     Beaucoup
    0.66
     väč
    0.65
     molta
    0.65
     molte
    0.64
     beaucoup
    0.64
     Molto
    0.63
     larger
    0.62
    Activations Density 0.014%

    No Known Activations