© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10712
    Prev
    Next
    INDEX
    Explanations

    references to behavior and behavioral changes

    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
    risten
    -0.69
     Milne
    -0.68
     Laurens
    -0.68
     Clooney
    -0.66
     gzip
    -0.62
     Koning
    -0.62
     Clarkson
    -0.61
     deadline
    -0.61
    tigma
    -0.61
    amak
    -0.61
    POSITIVE LOGITS
     behavior
    2.89
     Behavior
    2.68
     behaviour
    2.67
    behavior
    2.55
     behaviors
    2.51
     BEHAVIOR
    2.49
    Behavior
    2.39
     Behaviour
    2.38
    behaviour
    2.31
     behaviours
    2.30
    Activations Density 0.091%

    No Known Activations