© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 2459
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the name "Kim" and specific formatting characters or elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     return
    -0.54
     better
    -0.48
     advance
    -0.47
     power
    -0.46
     connect
    -0.44
     own
    -0.44
    return
    -0.44
     exchange
    -0.44
    	
    -0.43
    LORE
    -0.42
    POSITIVE LOGITS
     kasarigan
    1.12
     EconPapers
    0.84
    ViewFeatures
    0.79
     defaultstate
    0.79
     للاسماء
    0.75
     Normdatei
    0.74
    SharedDtor
    0.72
     ExecuteAsync
    0.70
     дописавши
    0.70
    AutoScaleMode
    0.70
    Activations Density 0.336%

    No Known Activations