© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10984
    Prev
    Next
    INDEX
    Explanations

    references to sound and audio characteristics

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

    references to sound or audio in text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     confronti
    -0.46
    hip
    -0.43
     dintre
    -0.42
     lộ
    -0.42
    itae
    -0.41
     office
    -0.41
    проце
    -0.41
    PageFactory
    -0.40
     Bec
    -0.39
     Jep
    -0.39
    POSITIVE LOGITS
    Sound
    1.13
     Sound
    1.11
     SOUND
    1.10
    SOUND
    0.98
     sound
    0.96
    sound
    0.95
     Sounds
    0.88
    Sounds
    0.84
     sounded
    0.82
    sounds
    0.77
    Activations Density 0.051%

    No Known Activations