© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 402
    Prev
    Next
    INDEX
    Explanations

    terms related to audio signal processing and sound quality enhancement

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Audio or frequency response curves/filters

    np_acts-logits-general · gemini-2.0-flash

    frequency response curve and filters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Personendaten
    -0.61
     validamos
    -0.43
    onOptions
    -0.42
     rep
    -0.42
    EndGlobalSection
    -0.42
    eddable
    -0.41
     repo
    -0.41
     suff
    -0.41
    تفصیلات
    -0.40
     flash
    -0.40
    POSITIVE LOGITS
     accidentes
    0.48
     salvaje
    0.44
     mío
    0.43
     kertas
    0.43
     botella
    0.42
     varandra
    0.42
     Económica
    0.41
     poussière
    0.41
     prioridad
    0.40
     transición
    0.40
    Activations Density 0.674%

    No Known Activations