© 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. 4408
    Prev
    Next
    INDEX
    Explanations

    heavyweight athletes and their physical attributes

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

    "huge" or "massive" things

    np_acts-logits-general · gemini-2.0-flash

    large, heavy, or bulky things

    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
     tiny
    -0.65
    Small
    -0.62
     small
    -0.62
     Small
    -0.60
    เล็ก
    -0.56
     JpaRepository
    -0.55
     infinitesimal
    -0.53
     Tiny
    -0.53
    Tiny
    -0.53
     flit
    -0.52
    POSITIVE LOGITS
     giant
    1.22
     behe
    1.20
     heavyweight
    1.12
     gigantic
    1.11
     massive
    1.10
    giant
    1.09
     mammoth
    1.04
    Massive
    1.03
     bulky
    1.02
    massive
    1.02
    Activations Density 0.340%

    No Known Activations