© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 17760
    Prev
    Next
    INDEX
    Explanations

    instances of structural or formal elements commonly used in programming or data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onded
    -0.69
    󠁿
    -0.63
     AUSSI
    -0.63
    mnop
    -0.60
    labus
    -0.60
    íqu
    -0.58
    hoeddwyd
    -0.58
     оригіналу
    -0.57
     kasarigan
    -0.57
    obby
    -0.57
    POSITIVE LOGITS
    ConstraintMaker
    0.69
    SOUNDBITE
    0.49
     indisponible
    0.46
    lotl
    0.44
    Twig
    0.42
     архивлан
    0.41
    SBATCH
    0.40
    EUROPA
    0.40
     cramp
    0.40
    copyWith
    0.40
    Activations Density 0.113%

    No Known Activations