© 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. 20-GEMMASCOPE-RES-16K
    11. 7286
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental conservation and habitat characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Woodland or forest environments

    np_acts-logits-general · gemini-2.0-flash

    forests woodlands and meadows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Externe
    -0.47
     externi
    -0.45
    layui
    -0.43
     Wikimedijinoj
    -0.42
     tế
    -0.41
     ModelRenderer
    -0.41
     MainAxisSize
    -0.39
     External
    -0.39
    مئ
    -0.39
    External
    -0.38
    POSITIVE LOGITS
     woods
    1.19
     forest
    1.14
     forests
    1.14
     woodland
    1.14
     woodlands
    1.10
     forested
    1.08
     wooded
    1.07
     thicket
    0.98
     scrub
    0.96
     grassland
    0.96
    Activations Density 0.294%

    No Known Activations