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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 5985
    Prev
    Next
    INDEX
    Explanations

    mentions of vibrations in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    vibration peak and amplitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     López
    -0.47
     Sánchez
    -0.45
     decret
    -0.44
     McP
    -0.43
    downs
    -0.42
     Cáceres
    -0.42
    ROE
    -0.42
    它
    -0.41
     القص
    -0.40
    ook
    -0.40
    POSITIVE LOGITS
     Vibration
    1.01
    Vibration
    0.94
     vibration
    0.94
     Vibe
    0.93
    Vib
    0.88
     Vib
    0.87
    vibration
    0.86
     Vibr
    0.85
    VIAF
    0.83
     vibrate
    0.83
    Activations Density 0.004%

    No Known Activations