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. 12-GEMMASCOPE-RES-16K
    6. 4707
    Prev
    Next
    INDEX
    Explanations

    events involving fleeing or leaving a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    niająca
    -0.55
    plin
    -0.50
    ագրություններ
    -0.50
    rilis
    -0.50
    Зноскі
    -0.48
    <bos>
    -0.46
    empêcher
    -0.46
    addCriterion
    -0.45
    BagLayout
    -0.44
    toCharArray
    -0.44
    POSITIVE LOGITS
     leaving
    0.84
     away
    0.72
     leave
    0.70
     departure
    0.70
    Leaving
    0.69
     Leaving
    0.69
    leaving
    0.69
     bezeichneter
    0.67
     parting
    0.63
     LEAVE
    0.62
    Activations Density 0.253%

    No Known Activations