© 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 - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2515
    Prev
    Next
    INDEX
    Explanations

    the word "pull" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymce
    -0.68
    Referanser
    -0.62
    gameserver
    -0.58
    Personensuche
    -0.57
    XmlAccessType
    -0.56
     Karsten
    -0.55
    XmlAccessorType
    -0.55
     Lordships
    -0.54
     lamella
    -0.53
    Abp
    -0.52
    POSITIVE LOGITS
     pull
    1.81
     pulled
    1.79
     Pull
    1.78
     pulling
    1.76
    pull
    1.76
     PULL
    1.75
    Pull
    1.74
     Pulling
    1.67
     pulls
    1.66
    Pulling
    1.66
    Activations Density 0.143%

    No Known Activations