© 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 - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1155
    Prev
    Next
    INDEX
    Explanations

    phrases related to complex or multifaceted concepts, particularly in scientific or analytical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.92
    .
    -0.90
     ilustracji
    -0.86
    :
    -0.78
    ;
    -0.75
     serca
    -0.75
     zprávy
    -0.73
     massa
    -0.72
    ↵↵
    -0.71
    (
    -0.71
    POSITIVE LOGITS
    ſelves
    1.60
    ſelf
    1.51
    ſem
    1.45
     Anſ
    1.44
     Reſ
    1.40
     Efq
    1.40
    neſs
    1.39
    IBLIO
    1.37
    leſs
    1.37
     ſind
    1.35
    Activations Density 2.423%

    No Known Activations