© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 39461
    Prev
    Next
    INDEX
    Explanations

    phrases that express alternatives or comparisons between different options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.84
    WithIOException
    -0.81
    AccessFile
    -0.78
    sizeCache
    -0.74
    eraard
    -0.68
     eventualmente
    -0.64
    همچنین
    -0.64
     Tempest
    -0.63
    kadang
    -0.63
    zyści
    -0.62
    POSITIVE LOGITS
    Instead
    0.74
     Instead
    0.73
     Rather
    0.62
     Statt
    0.59
     idea
    0.59
     let
    0.57
    Rather
    0.57
     instead
    0.56
     direct
    0.56
     being
    0.55
    Activations Density 0.024%

    No Known Activations