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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11762
    Prev
    Next
    INDEX
    Explanations

    references to sound and audio-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trip
    -0.47
     confronti
    -0.43
    TabPage
    -0.43
    事は
    -0.42
    stufen
    -0.40
    subpackage
    -0.40
     taxon
    -0.40
     féd
    -0.40
    hips
    -0.40
     proxy
    -0.40
    POSITIVE LOGITS
    Sound
    1.02
     Sound
    0.96
     SOUND
    0.95
    SOUND
    0.88
    sound
    0.85
     sound
    0.83
     sounded
    0.74
     Sounds
    0.74
    Sounds
    0.72
     geluid
    0.69
    Activations Density 0.136%

    No Known Activations