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. 3-GEMMASCOPE-RES-16K
    6. 10865
    Prev
    Next
    INDEX
    Explanations

    phrases related to disconnection or stopping actions

    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
    arschijnlijk
    -0.60
    )?;
    -0.58
     Charged
    -0.53
    underscore
    -0.52
     Waray
    -0.50
    ++);
    -0.49
     charged
    -0.49
     dusting
    -0.48
     المد
    -0.47
    Personensuche
    -0.47
    POSITIVE LOGITS
     interrom
    0.86
     interruption
    0.83
    قطع
    0.81
     interruptions
    0.78
     severed
    0.72
     interrup
    0.72
     interrump
    0.71
     cutoff
    0.68
    断
    0.67
     switching
    0.67
    Activations Density 0.563%

    No Known Activations