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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 74956
    Prev
    Next
    INDEX
    Explanations

    instances of the word "called."

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

    what something is called

    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
    Kanpo
    -0.46
     dieß
    -0.43
     juſ
    -0.43
     pylint
    -0.43
     fédé
    -0.43
    rocław
    -0.40
     Urteil
    -0.40
     viñ
    -0.40
     gethan
    -0.40
     húmedo
    -0.40
    POSITIVE LOGITS
     CALLED
    0.95
    called
    0.94
     Called
    0.94
     called
    0.91
    Called
    0.90
    createElement
    0.72
    ]=="
    0.69
    getElementById
    0.68
    叫做
    0.67
     chamado
    0.65
    Activations Density 0.013%

    No Known Activations