© 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. 25-GEMMASCOPE-RES-16K
    11. 7393
    Prev
    Next
    INDEX
    Explanations

    numerals and specific words in various languages or scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ه
    -0.81
    م
    -0.67
    у
    -0.66
    ي
    -0.65
    ο
    -0.63
     själva
    -0.62
    \{\\
    -0.62
    ر
    -0.62
    е
    -0.58
    י
    -0.56
    POSITIVE LOGITS
    featureID
    0.54
    e
    0.51
    وفاته
    0.48
    يكب
    0.46
    B
    0.43
     NPs
    0.42
    IndentedString
    0.41
     characterised
    0.41
    J
    0.40
    moga
    0.40
    Activations Density 0.019%

    No Known Activations