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. 20-GEMMASCOPE-RES-16K
    6. 2697
    Prev
    Next
    INDEX
    Explanations

    words related to listening or hearing

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

    "hear" and its forms

    np_acts-logits-general · gemini-2.0-flash

    hearing voices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    SharedDtor
    -0.88
    VIAF
    -0.73
     nahilalakip
    -0.68
    ništvo
    -0.68
     Picchu
    -0.67
    ьаж
    -0.66
    modelBuilder
    -0.66
     nakalista
    -0.66
     OFDb
    -0.64
    WriteTagHelper
    -0.63
    POSITIVE LOGITS
     hears
    0.84
     voices
    0.84
     hear
    0.83
     about
    0.82
    👂
    0.82
     heard
    0.78
     parler
    0.77
     Hear
    0.75
    Hear
    0.74
     Hearn
    0.74
    Activations Density 0.049%

    No Known Activations