© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10640
    Prev
    Next
    INDEX
    Explanations

    patterns related to hierarchical structures in data, particularly in coding or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (@"%@",
    -0.68
    limin
    -0.67
    جغرافيا
    -0.66
    frow
    -0.65
    pulumi
    -0.63
     mira
    -0.61
    [];
    -0.61
    月から
    -0.61
     McCormack
    -0.61
    nete
    -0.60
    POSITIVE LOGITS
     coraggio
    0.70
     ویکی‌پدی
    0.68
     quelcon
    0.67
    <bos>
    0.66
     richiesto
    0.65
    cessite
    0.64
    richting
    0.63
     samarbeid
    0.63
     sentimenti
    0.62
     défauts
    0.61
    Activations Density 0.257%

    No Known Activations