© 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. 91208
    Prev
    Next
    INDEX
    Explanations

    instances and variations of the word "reverse"

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

    reversing or rotating

    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
     المعيارى
    -0.79
     informée
    -0.73
    帖最后由
    -0.72
     للمعارف
    -0.67
    PerformLayout
    -0.67
     nakalista
    -0.66
    principalColumn
    -0.66
    endpush
    -0.64
    mobileqq
    -0.64
    
    -0.62
    POSITIVE LOGITS
     sequence
    0.36
     Char
    0.36
     Schell
    0.36
     Ver
    0.36
     output
    0.35
     search
    0.34
     segments
    0.34
    ing
    0.34
    NSMutable
    0.33
     ver
    0.33
    Activations Density 0.014%

    No Known Activations