© 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. 1519
    Prev
    Next
    INDEX
    Explanations

    references to downloadable content and free software

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

    game modifications ("mods")

    np_acts-logits-general · gemini-2.0-flash

    install, play, mod

    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
     jspb
    -0.69
    NamedQuery
    -0.65
     يتيمه
    -0.61
    MethodManager
    -0.59
     Vikipedi
    -0.59
    ItemBackground
    -0.59
    jspx
    -0.58
    ftagPool
    -0.56
     //$
    -0.55
    AxisAlignment
    -0.53
    POSITIVE LOGITS
     mod
    1.02
     mods
    1.01
     modding
    0.97
     modded
    0.94
     Mods
    0.78
     Mod
    0.77
    Mod
    0.77
    mods
    0.76
    mod
    0.75
     textures
    0.74
    Activations Density 0.377%

    No Known Activations