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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 6668
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "list"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.72
    ()?;
    -0.69
     ſmall
    -0.66
     poffible
    -0.65
     bornes
    -0.64
     otomatig
    -0.64
     cappuccio
    -0.64
     GenerationType
    -0.62
    polation
    -0.62
     препратки
    -0.62
    POSITIVE LOGITS
    list
    3.56
     list
    2.95
    LIST
    2.62
    List
    2.56
     List
    2.55
     LIST
    2.48
    lists
    2.48
     lists
    2.28
     Lists
    2.09
    Lists
    1.91
    Activations Density 0.061%

    No Known Activations