© 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. 20-GEMMASCOPE-RES-131K
    11. 108087
    Prev
    Next
    INDEX
    Explanations

    expressions of confusion or bewilderment

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

    puzzled, incomprehensible, or unexplained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onPostExecute
    -0.56
    SBATCH
    -0.53
    Personensuche
    -0.52
    
    -0.52
    StoryboardSegue
    -0.52
    VideoCapture
    -0.52
    OGND
    -0.52
    Cyfeiriadau
    -0.51
     Photocase
    -0.50
    ThroughAttribute
    -0.50
    POSITIVE LOGITS
    不解
    0.75
     puzzling
    0.75
     puzzled
    0.74
     perplexing
    0.74
     baffling
    0.72
     perplexed
    0.70
     bewilder
    0.69
     bewildered
    0.68
     baffled
    0.63
     inexplicable
    0.61
    Activations Density 0.034%

    No Known Activations