© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3691
    Prev
    Next
    INDEX
    Explanations

    items related to cooking and kitchen appliances

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

    Adjectives preceding nouns

    np_acts-logits-general · gemini-2.0-flash

    these or those followed by another thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     restantes
    -0.57
    自身
    -0.57
     asimismo
    -0.57
    ())));
    -0.57
     pleaſure
    -0.56
     quæ
    -0.56
     sağlar
    -0.56
    tır
    -0.55
    一方で
    -0.55
    いかがでしょうか
    -0.55
    POSITIVE LOGITS
     weird
    1.58
    weird
    1.38
     shitty
    1.36
     thingy
    1.30
     crappy
    1.29
     fucking
    1.27
     pretty
    1.22
     stuff
    1.21
     stupid
    1.20
     weirdly
    1.20
    Activations Density 0.509%

    No Known Activations