© 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 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. 13106
    Prev
    Next
    INDEX
    Explanations

    instances of the term "fac" and its variations

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

    after "fac" or "Rub" at the start of the word

    np_acts-logits-general · gemini-2.0-flash

    factitious, facilitation or rub

    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
     felé
    -0.44
    vär
    -0.42
     Dillon
    -0.41
    quelize
    -0.41
     Vite
    -0.40
     die
    -0.39
    maksi
    -0.39
     point
    -0.39
    cjach
    -0.38
    chakra
    -0.38
    POSITIVE LOGITS
    #+#
    0.88
    lapsingToolbar
    0.79
     ModelExpression
    0.76
     كومونز
    0.76
    jsxFileName
    0.76
    AutoScaleMode
    0.70
    تقاوى
    0.69
     nahilalakip
    0.69
    出版年
    0.67
    ValueStyle
    0.66
    Activations Density 0.479%

    No Known Activations