© 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. 8721
    Prev
    Next
    INDEX
    Explanations

    references to quantities or measurements

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

    French text or language indicators

    np_acts-logits-general · gemini-2.0-flash

    bonne soirée

    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
    DrawerToggle
    -0.55
     Oso
    -0.54
    enumi
    -0.53
     Lafayette
    -0.53
    Originally
    -0.52
    ณี
    -0.50
     lemp
    -0.50
    şiv
    -0.50
    enet
    -0.49
    ("."
    -0.49
    POSITIVE LOGITS
    GEBURTS
    0.68
     JOUR
    0.58
     NavController
    0.56
     Chwiliwch
    0.53
    DockStyle
    0.49
    CDATA
    0.48
    +#+
    0.47
     jour
    0.47
     chande
    0.46
     mai
    0.46
    Activations Density 0.074%

    No Known Activations