© 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. 23-GEMMASCOPE-RES-16K
    11. 8300
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to speech synthesis and audio handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 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
    ']=='
    -0.44
     дописавши
    -0.43
    devamını
    -0.41
     esternos
    -0.39
    تقاوى
    -0.38
    ]=='
    -0.37
    "]=
    -0.36
     judíos
    -0.36
    ########.
    -0.36
    TypedDataSet
    -0.36
    POSITIVE LOGITS
    MessageTagHelper
    0.75
     GenerationType
    0.62
    tagHelperRunner
    0.59
    migrationBuilder
    0.54
     Bekasi
    0.52
     Nusantara
    0.52
     аппарат
    0.49
     userRepository
    0.49
    ſelf
    0.49
     PCP
    0.48
    Activations Density 0.221%

    No Known Activations