Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 70986
    Prev
    Next
    INDEX
    Explanations

    instances of the word "printed" and its variations

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

    printed matter and circuits

    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
     vault
    -0.49
    MethodManager
    -0.48
     Ausnahme
    -0.47
     reaſon
    -0.47
    Serviço
    -0.47
     للمعارف
    -0.46
    sibilité
    -0.46
    sapato
    -0.46
     ambulance
    -0.46
     Schwerpunkt
    -0.46
    POSITIVE LOGITS
     printed
    1.64
    Printed
    1.56
     Printed
    1.56
    printed
    1.52
     PRINTED
    1.31
     imprimé
    0.82
     imprimée
    0.81
     impreso
    0.80
    written
    0.71
     written
    0.69
    Activations Density 0.006%

    No Known Activations