© 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. 64364
    Prev
    Next
    INDEX
    Explanations

    the word "both" and its variations, indicating the presence of duality or paired concepts

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

    both

    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
     forskellige
    -0.41
     vários
    -0.39
     various
    -0.38
     berbagai
    -0.38
     consultato
    -0.37
     bepaalde
    -0.37
     allerlei
    -0.35
     pelbagai
    -0.35
     giusta
    -0.35
    様々な
    -0.34
    POSITIVE LOGITS
    ⟬
    0.72
     figur
    0.71
     sides
    0.70
     Sides
    0.69
    styleType
    0.68
    sides
    0.68
     للمعارف
    0.68
     صوتيه
    0.66
     '\\;'
    0.64
    ьаж
    0.63
    Activations Density 0.045%

    No Known Activations