© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 9696
    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 @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    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
    -0.75
      
    -0.60
    ordning
    -0.55
     m
    -0.54
    ChromeDriver
    -0.54
    dirs
    -0.53
     questão
    -0.53
     chère
    -0.53
     отношению
    -0.52
    DefaultValue
    -0.51
    POSITIVE LOGITS
     Capture
    2.26
     capture
    2.23
     captures
    2.20
    capture
    2.09
    Capture
    2.08
     CAPT
    1.99
     captured
    1.97
    captures
    1.91
     capturing
    1.87
     captur
    1.84
    Activations Density 0.047%

    No Known Activations