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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12947
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to chaos and disruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.52
    Jeografia
    -0.46
     Biôgrafia
    -0.45
     typelib
    -0.45
    issauga
    -0.40
     Мексичка
    -0.40
    Terima
    -0.40
     consentement
    -0.39
    inheritdoc
    -0.39
     nakalista
    -0.38
    POSITIVE LOGITS
     turbul
    0.85
     Turbulence
    0.82
     turbulence
    0.79
     NOISE
    0.75
     Disturb
    0.75
    chaos
    0.75
     Turbul
    0.75
     disturbances
    0.73
     chaos
    0.73
    trouble
    0.72
    Activations Density 0.379%

    No Known Activations