© 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. 97366
    Prev
    Next
    INDEX
    Explanations

    the word "each" used to signify repetition or enumeration in various contexts

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

    each followed by a singular noun

    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
    SourceChecksum
    -0.63
    PyExc
    -0.59
     ujednoznacz
    -0.58
    ⟬
    -0.58
     kohdetta
    -0.57
     الرياضيه
    -0.55
    
    -0.54
     utafitiHapana
    -0.54
    genheim
    -0.53
    IndentedString
    -0.53
    POSITIVE LOGITS
    Each
    1.19
     Each
    1.16
    Every
    1.00
     Every
    0.98
     Chaque
    0.91
    Chaque
    0.91
     Setiap
    0.85
    Cada
    0.80
     Ogni
    0.80
     Cada
    0.79
    Activations Density 0.020%

    No Known Activations