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. 13-GEMMASCOPE-RES-16K
    6. 16306
    Prev
    Next
    INDEX
    Explanations

    verbs related to pursuit or escape

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vocale
    -0.63
     froide
    -0.53
     sond
    -0.52
     artistico
    -0.52
    writeField
    -0.52
     Rebuild
    -0.51
    henge
    -0.51
     متحده
    -0.50
    thanes
    -0.50
     trầm
    -0.50
    POSITIVE LOGITS
     escape
    1.05
     escaping
    1.04
     escaped
    1.01
    escaping
    0.96
     fleeing
    0.95
     evade
    0.94
     escapes
    0.92
    逃
    0.90
     Escape
    0.88
     evasion
    0.85
    Activations Density 0.259%

    No Known Activations