© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2118
    Prev
    Next
    INDEX
    Explanations

    information about biodiversity and plant species in a specific ecological context

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

    biodiversity and species counts

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     ModelExpression
    -0.82
    хьтан
    -0.67
     externi
    -0.64
    diyesi
    -0.63
    tagext
    -0.63
    ScopeManager
    -0.60
     newBuilder
    -0.56
     pageContext
    -0.54
    Filmografia
    -0.50
     distanciation
    -0.50
    POSITIVE LOGITS
     biodiversity
    1.50
     species
    1.43
     diversity
    1.28
     fauna
    1.17
     flora
    1.15
     Biodiversity
    1.14
     Species
    1.14
    diversity
    1.10
    Biodiversity
    1.10
    species
    1.08
    Activations Density 0.184%

    No Known Activations