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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6099
    Prev
    Next
    INDEX
    Explanations

    nouns or names related to locations and organizations

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

    Tokens after "N" or "Man" followed by "zini"

    np_acts-logits-general · gemini-2.0-flash

    Manzini and Manicaland

    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
    NOPQRST
    -0.61
     <=",
    -0.56
    Vaata
    -0.55
    Vezi
    -0.55
    CloseOperation
    -0.54
    XmlAccessorType
    -0.54
    Varint
    -0.52
    зулта
    -0.52
    انيف
    -0.52
    BagConstraints
    -0.51
    POSITIVE LOGITS
    viewDidLoad
    0.59
     derra
    0.43
     ferme
    0.42
    Билгалдахарш
    0.42
     extérieurs
    0.42
    σθαι
    0.41
    de
    0.40
    deh
    0.40
     yuri
    0.40
     DataLoader
    0.39
    Activations Density 0.099%

    No Known Activations