© 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. 14705
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or connections between concepts

    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
    cadilly
    -0.70
     ​​
    -0.69
    kwds
    -0.62
     pikir
    -0.61
     newUser
    -0.61
     NDEBUG
    -0.60
     façons
    -0.60
    AsUp
    -0.60
    kfree
    -0.59
     Denton
    -0.59
    POSITIVE LOGITS
     Correspond
    1.26
     correspond
    1.21
    Correspond
    1.18
     corrispond
    1.14
    correspond
    1.13
     corresponds
    1.12
     correspondents
    1.07
     CORRESPOND
    1.06
     correspondant
    1.05
    Correspondence
    1.02
    Activations Density 0.026%

    No Known Activations