© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12922
    Prev
    Next
    INDEX
    Explanations

    mentions of biodiversity and species counts within specific ecological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.88
    RenderAtEndOf
    -0.73
     esternos
    -0.73
     informée
    -0.71
     صوتيه
    -0.66
    ChildScrollView
    -0.65
     EconPapers
    -0.62
    IVEREF
    -0.62
    RTDA
    -0.61
     OFDb
    -0.60
    POSITIVE LOGITS
     biodiversity
    0.49
     creatures
    0.49
     species
    0.46
     wild
    0.42
     biological
    0.41
     biologists
    0.41
     biodivers
    0.40
     fauna
    0.39
     bio
    0.38
     ecosystems
    0.38
    Activations Density 0.385%

    No Known Activations