© 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. 24-GEMMASCOPE-RES-16K
    6. 5039
    Prev
    Next
    INDEX
    Explanations

    specific cooking measurements and instructions

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

    Before a verb or adjective

    np_acts-logits-general · gemini-2.0-flash

    careful not to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LLocation
    -0.53
    hluk
    -0.50
     saira
    -0.49
    cknow
    -0.49
    Literatuur
    -0.49
     kautta
    -0.49
    enseits
    -0.48
    bibinfo
    -0.45
     Ergän
    -0.44
     возгла
    -0.44
    POSITIVE LOGITS
     thicker
    0.90
     sanding
    0.89
     rinsing
    0.81
     removing
    0.81
     Removing
    0.81
    Removing
    0.80
     sanded
    0.80
     gluing
    0.80
     thinner
    0.77
     sandpaper
    0.77
    Activations Density 0.456%

    No Known Activations