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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 694
    Prev
    Next
    INDEX
    Explanations

    phrases or constructions that start with the word "having."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chisholm
    -0.67
     Tate
    -0.66
    símbolo
    -0.64
    prozess
    -0.60
     StyleSheet
    -0.59
    newVal
    -0.59
     собой
    -0.58
     Chry
    -0.57
    chieht
    -0.57
    DoubleQuotes
    -0.57
    POSITIVE LOGITS
    having
    1.98
     having
    1.93
     Having
    1.92
    Having
    1.90
     HAVING
    1.85
     avendo
    1.10
     ayant
    1.07
     havi
    1.03
     habiendo
    0.99
    ayant
    0.93
    Activations Density 0.084%

    No Known Activations