Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9307
    Prev
    Next
    INDEX
    Explanations

    phrases and variations of the word "pull."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    XmlAccessType
    -0.78
    Personensuche
    -0.77
    XmlAccessorType
    -0.75
     onOptions
    -0.74
     postIndex
    -0.73
    esModule
    -0.68
     ©️
    -0.65
    المشاركات
    -0.64
     contextLoads
    -0.61
    SafeMath
    -0.60
    POSITIVE LOGITS
     pull
    1.64
    pull
    1.54
     Pull
    1.53
     pulls
    1.52
     pulled
    1.50
     pulling
    1.49
    Pull
    1.47
     PULL
    1.46
     Pulling
    1.41
    PULL
    1.32
    Activations Density 0.077%

    No Known Activations