© 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. 15-GEMMASCOPE-RES-16K
    11. 5233
    Prev
    Next
    INDEX
    Explanations

    special characters or markers related to different types of content or segments in a dataset

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Czytaj
    -0.40
    Obrigada
    -0.33
     inmigrantes
    -0.29
     encaje
    -0.28
     împ
    -0.27
     Grüsse
    -0.27
     hjemmeside
    -0.26
     sufri
    -0.26
     intelig
    -0.26
     beira
    -0.26
    POSITIVE LOGITS
    Hochspringen
    0.65
    ollectionView
    0.62
    RTEX
    0.61
    msgTypes
    0.61
    ardless
    0.60
     tera
    0.60
     $_(
    0.60
    ㊃
    0.60
    PathVariable
    0.59
    bronze
    0.59
    Activations Density 0.009%

    No Known Activations