© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12765
    Prev
    Next
    INDEX
    Explanations

    elements and entities related to music and entertainment contexts

    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
    󠁴
    -0.44
     .
    -0.36
     pido
    -0.35
     dejo
    -0.34
    AddHtmlAttribute
    -0.32
     Reco
    -0.32
    رشف
    -0.32
     sheet
    -0.32
    füllung
    -0.31
    etzal
    -0.31
    POSITIVE LOGITS
    +#+#
    0.77
     nakalista
    0.74
     iNdEx
    0.67
     Efq
    0.61
    featureID
    0.61
     snippetHide
    0.59
     CURIAM
    0.58
    ſelf
    0.58
     ddelweddau
    0.57
     AssemblyCulture
    0.57
    Activations Density 2.013%

    No Known Activations