© 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. 16-GEMMASCOPE-RES-16K
    11. 3890
    Prev
    Next
    INDEX
    Explanations

    references to sound and audio quality

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

    "sound"

    np_acts-logits-general · gemini-2.0-flash

    sound descriptors or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.80
    Rujuakan
    -0.77
     Reeve
    -0.73
     Twp
    -0.73
    Gemeinden
    -0.72
     täv
    -0.72
     sfida
    -0.72
    Према
    -0.71
     elbows
    -0.71
     Montoya
    -0.70
    POSITIVE LOGITS
     SOUND
    1.22
     sounds
    1.16
     Sound
    1.12
     sound
    1.12
     sounded
    1.08
    SOUND
    1.07
    Sound
    1.02
     Sounds
    1.00
    sound
    0.97
    Sounds
    0.95
    Activations Density 0.155%

    No Known Activations