© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 9915
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Sur" and its variations, indicating a focus on a specific subject or character in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fonseca
    -0.70
     pstmt
    -0.68
    __(/*!
    -0.63
    ../../
    -0.61
     Cleveland
    -0.58
    PULL
    -0.57
    getFullYear
    -0.56
    leine
    -0.56
    LEG
    -0.56
    umente
    -0.55
    POSITIVE LOGITS
    SUR
    1.16
     SUR
    1.16
    Sur
    1.14
    sur
    1.07
     Sur
    1.04
     Sury
    0.87
     UR
    0.87
     Suriname
    0.86
     Surve
    0.84
    ur
    0.84
    Activations Density 0.139%

    No Known Activations