© 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. 1746
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or landforms

    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
     spesa
    -0.66
     presença
    -0.58
     poussière
    -0.58
     exportación
    -0.57
     ști
    -0.54
     lápiz
    -0.54
     sentenza
    -0.53
     decoracion
    -0.53
     pronti
    -0.52
     cấu
    -0.51
    POSITIVE LOGITS
    land
    1.37
    wood
    1.17
    LAND
    1.10
    lands
    1.10
    field
    1.02
     Efq
    0.94
    stone
    0.93
    ville
    0.90
     itſelf
    0.90
    brooke
    0.88
    Activations Density 0.347%

    No Known Activations