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. 75365
    Prev
    Next
    INDEX
    Explanations

    references to sound or sound-related terms

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

    phrases containing sound

    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
     marito
    -0.49
    itae
    -0.48
     lộ
    -0.46
     dintre
    -0.45
    DotNetBar
    -0.45
     moglie
    -0.44
     plupart
    -0.43
     EEC
    -0.43
     colleague
    -0.43
     solito
    -0.42
    POSITIVE LOGITS
    Sound
    1.13
     Sound
    1.12
     SOUND
    1.09
    SOUND
    0.96
    sound
    0.92
     sound
    0.92
     Sounds
    0.84
    Sounds
    0.78
     Soud
    0.73
     SoundCloud
    0.72
    Activations Density 0.011%

    No Known Activations