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. 21-GEMMASCOPE-RES-16K
    6. 7384
    Prev
    Next
    INDEX
    Explanations

    references to chaos and disorder in events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reverso
    -0.57
    setVerticalGroup
    -0.57
     muualla
    -0.52
    httphttps
    -0.52
    jshint
    -0.52
     sympy
    -0.51
     duduk
    -0.49
    ScopeManager
    -0.49
    AutoField
    -0.49
     Durand
    -0.49
    POSITIVE LOGITS
     chaos
    1.82
    chaos
    1.49
     chaotic
    1.47
     commotion
    1.35
     caos
    1.35
     mayhem
    1.32
    Chaos
    1.32
     frenzy
    1.31
     rush
    1.27
     Chaos
    1.27
    Activations Density 0.274%

    No Known Activations