© 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. 18-GEMMASCOPE-RES-16K
    11. 16289
    Prev
    Next
    INDEX
    Explanations

    elements related to wildlife and animal behavior

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

    Animals, especially deer and small mammals

    np_acts-logits-general · gemini-2.0-flash

    deer and wildlife

    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
    InsertCommand
    -0.56
     оригіналу
    -0.49
     geografic
    -0.48
    adaptiveStyles
    -0.48
     combusti
    -0.46
     Nozzle
    -0.46
     stamens
    -0.45
     origini
    -0.44
    ServletConfig
    -0.43
    سمبر
    -0.43
    POSITIVE LOGITS
     deer
    1.09
     animals
    0.93
     rabbits
    0.85
    deer
    0.85
     Deer
    0.84
     animal
    0.83
     wildlife
    0.82
    Deer
    0.81
     rabbit
    0.78
     sheep
    0.77
    Activations Density 0.207%

    No Known Activations