© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6912
    Prev
    Next
    INDEX
    Explanations

    terms related to biodiversity and ecosystem diversity

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

    Mentions species diversity or richness

    np_acts-logits-general · gemini-2.0-flash

    rich species biodiversity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    -1.00
     propOrder
    -0.77
     externi
    -0.73
    хьтан
    -0.69
    Carriera
    -0.65
     newBuilder
    -0.65
     оригіналу
    -0.63
    thâu
    -0.61
    ScopeManager
    -0.60
     متعلقه
    -0.60
    POSITIVE LOGITS
     biodiversity
    1.33
     species
    1.21
     diversity
    1.10
     flora
    0.98
     fauna
    0.97
    diversity
    0.94
     wildlife
    0.94
     Biodiversity
    0.92
    Biodiversity
    0.91
     biodivers
    0.88
    Activations Density 0.303%

    No Known Activations