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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 303
    Prev
    Next
    INDEX
    Explanations

    mentions of various animal species or references to animals in general

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

    pets, animals, and animal care

    np_acts-logits-general · gemini-2.0-flash

    raising and housing animals

    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
     StringTokenizer
    -0.58
     Zahn
    -0.56
    dehydes
    -0.53
     @"/
    -0.49
     समीक्षक
    -0.47
     lignin
    -0.45
    vaadin
    -0.45
     woodpecker
    -0.44
    ıntı
    -0.44
    Tracce
    -0.43
    POSITIVE LOGITS
     pets
    0.92
     pet
    0.87
     aquarium
    0.86
     caged
    0.85
     breeding
    0.82
     rearing
    0.81
     tamed
    0.76
     indoor
    0.76
     exotic
    0.76
     reared
    0.76
    Activations Density 0.329%

    No Known Activations