© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76717
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'D' with high frequency

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

    D at start of words and journal series

    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
     toalla
    -0.73
     orilla
    -0.68
     cejas
    -0.67
     atmósfera
    -0.66
     desmotivaciones
    -0.66
     cooperación
    -0.66
     rodilla
    -0.66
     silicona
    -0.66
     pierna
    -0.65
     precisión
    -0.65
    POSITIVE LOGITS
     D
    1.98
    D
    1.52
     d
    1.14
    getD
    1.13
     Д
    1.07
    Д
    1.04
    Ｄ
    1.01
     B
    0.93
    pD
    0.93
    d
    0.92
    Activations Density 0.032%

    No Known Activations