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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 112
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their concentrations in experimental contexts

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

    Lab equipment/environment

    np_acts-logits-general · gemini-2.0-flash

    laboratory sample containers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recev
    -0.49
     Schulter
    -0.49
     réve
    -0.49
    Попис
    -0.49
     tjen
    -0.47
    lež
    -0.46
    Brainz
    -0.46
    ->_
    -0.45
    readystatechange
    -0.45
    ionView
    -0.45
    POSITIVE LOGITS
     laboratory
    0.81
     sample
    0.73
     glassware
    0.71
     Laboratory
    0.69
     Sample
    0.68
    sample
    0.67
     lab
    0.67
    Sample
    0.64
     Lab
    0.64
    Laboratory
    0.64
    Activations Density 1.679%

    No Known Activations