© 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. 7723
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and judicial processes

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

    Prepositions, conjunctions, and verb-related words

    np_acts-logits-general · gemini-2.0-flash

    remote control

    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
     Line
    -1.10
     Place
    -0.95
     Score
    -0.94
     Shot
    -0.94
     Charge
    -0.94
     Entry
    -0.93
     Scale
    -0.93
     Handle
    -0.91
     Room
    -0.90
     Point
    -0.89
    POSITIVE LOGITS
     site
    0.34
    Smarty
    0.30
    Semitic
    0.30
     Juventud
    0.30
     Carnaval
    0.30
     Cyberpunk
    0.30
     Evangelio
    0.29
     }}</
    0.29
    Zombies
    0.29
    Fahren
    0.29
    Activations Density 1.755%

    No Known Activations