© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5458
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to audio processing and synthesis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.60
    Datuak
    -0.51
     HttpNotFound
    -0.51
     Braw
    -0.50
    usehen
    -0.49
    henswürdigkeiten
    -0.49
    NetworkInfo
    -0.47
     fotográfico
    -0.47
     impresa
    -0.46
    فحه
    -0.46
    POSITIVE LOGITS
     audio
    2.20
     sound
    2.17
     Audio
    1.88
    sound
    1.87
     Sound
    1.86
    audio
    1.84
    Sound
    1.82
     SOUND
    1.81
    Audio
    1.78
     voice
    1.77
    Activations Density 0.624%

    No Known Activations