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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 6084
    Prev
    Next
    INDEX
    Explanations

    references to music recordings and their associated metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.61
    ſelf
    -0.59
     ***!
    -0.58
     AssemblyTitle
    -0.52
     Chwiliwch
    -0.50
    tagHelperRunner
    -0.50
    bleau
    -0.49
    NameInMap
    -0.48
     архивлан
    -0.47
    onOptions
    -0.47
    POSITIVE LOGITS
     vinyl
    1.10
     Vinyl
    0.96
     vinilo
    0.92
    Vinyl
    0.92
    vinyl
    0.91
     vinyle
    0.83
     vinil
    0.81
     turntable
    0.79
    レコード
    0.73
     viny
    0.73
    Activations Density 0.120%

    No Known Activations