© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1682
    Prev
    Next
    INDEX
    Explanations

    words and symbols in various languages, particularly focusing on specific characters and their instances

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

    Followed by punctuation and/or currency symbols

    np_acts-logits-general · gemini-2.0-flash

    foreign and historical names

    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
    RegressionTest
    -0.66
     calendriers
    -0.62
    PreferredItem
    -0.60
    twimg
    -0.58
    ه
    -0.57
    AsUp
    -0.57
    CloseOperation
    -0.57
    ipfel
    -0.55
    Bảo
    -0.55
     Exacts
    -0.55
    POSITIVE LOGITS
     Cæsar
    0.65
     Shakspeare
    0.62
     Sopho
    0.57
     himſelf
    0.57
    s
    0.55
    n
    0.55
    t
    0.55
    d
    0.54
    m
    0.54
    e
    0.54
    Activations Density 0.020%

    No Known Activations