© 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. 9-GEMMASCOPE-RES-131K
    6. 17174
    Prev
    Next
    INDEX
    Explanations

    phrases of gratitude or acknowledgment

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

    attributing reason thanks to

    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
     sucks
    -0.42
     Leer
    -0.40
    laps
    -0.40
     willy
    -0.40
     crap
    -0.39
    اریخ
    -0.37
     busted
    -0.37
     unacceptable
    -0.37
    lapse
    -0.37
    Ủ
    -0.36
    POSITIVE LOGITS
     Dzięki
    1.05
    Благодаря
    1.05
     dzięki
    1.04
     Благодаря
    1.04
     grâce
    0.96
     благодаря
    0.93
    âce
    0.92
     gracias
    0.92
    ďaka
    0.92
     grazie
    0.88
    Activations Density 0.007%

    No Known Activations