© 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. 31-GEMMASCOPE-RES-131K
    11. 1305
    Prev
    Next
    INDEX
    Explanations

    elements related to health and wellness, especially those emphasizing physical benefits

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

    as well, too

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     همچنین
    -0.93
     ayrıca
    -0.80
     նաև
    -0.74
     även
    -0.66
     또
    -0.61
    Also
    -0.60
    还
    -0.60
     Also
    -0.58
    همچنین
    -0.57
     myös
    -0.56
    POSITIVE LOGITS
     too
    2.06
    too
    1.45
    Too
    1.16
     aswell
    1.16
     TOO
    1.09
     Too
    1.05
     demasiado
    1.02
     demasi
    0.97
     troppo
    0.96
     тоже
    0.94
    Activations Density 0.382%

    No Known Activations