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. 3-GEMMASCOPE-RES-16K
    6. 7910
    Prev
    Next
    INDEX
    Explanations

    the concept of "capture" 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 @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AfterClass
    -0.73
     onOptions
    -0.66
     crois
    -0.57
     préf
    -0.52
     questão
    -0.51
      
    -0.51
    Dirs
    -0.51
    ös
    -0.50
     pat
    -0.50
     Yew
    -0.50
    POSITIVE LOGITS
     capture
    3.11
     Capture
    3.06
     captures
    2.88
    Capture
    2.82
    capture
    2.77
     captured
    2.58
     capturing
    2.54
    captures
    2.46
     CAPT
    2.42
    captured
    2.29
    Activations Density 0.051%

    No Known Activations