Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 13838
    Prev
    Next
    INDEX
    Explanations

    expressions and adjectives related to perfection and ideal attributes

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

    "perfect."

    np_acts-logits-general · gemini-2.0-flash

    perfect fit, timing, or storm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ancha
    -0.50
     wiser
    -0.50
    dafrika
    -0.48
     efectivo
    -0.48
    Controllo
    -0.48
     efficacement
    -0.47
     gruesa
    -0.46
    رشف
    -0.46
     erfolgreich
    -0.45
     Olympedia
    -0.45
    POSITIVE LOGITS
     imperfection
    1.01
     imperfect
    0.97
     timing
    0.95
     fit
    0.88
     IDEAL
    0.87
     Voraussetzungen
    0.87
     imperfections
    0.85
     match
    0.84
     suited
    0.84
     Timing
    0.84
    Activations Density 0.050%

    No Known Activations