© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1193
    Prev
    Next
    INDEX
    Explanations

    references to financial contributions or tips

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

    the word "tip" in contexts involving monetary transactions or gratuities.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المكت
    -0.39
     Pank
    -0.32
     Núñez
    -0.30
    ToMany
    -0.30
     مكت
    -0.30
     Knie
    -0.30
     OFDb
    -0.30
    oa̍t
    -0.29
    jooq
    -0.29
    rimônio
    -0.29
    POSITIVE LOGITS
     tip
    2.58
     Tip
    2.20
     tips
    2.19
    Tip
    2.17
    tip
    2.13
     tipped
    2.05
     tipping
    2.00
    tips
    1.95
     Tips
    1.92
    Tips
    1.87
    Activations Density 0.103%

    No Known Activations