© 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. 12-GEMMASCOPE-RES-16K
    6. 9405
    Prev
    Next
    INDEX
    Explanations

    C++ input and output stream operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stdio
    -0.90
    eves
    -0.75
     dynam
    -0.66
    Richie
    -0.66
     Shira
    -0.65
    chastic
    -0.64
    posits
    -0.63
    Errorf
    -0.62
    RepeatedField
    -0.61
    婿
    -0.60
    POSITIVE LOGITS
    Cout
    1.64
     Cout
    1.46
     cout
    1.42
    cout
    1.37
     Coutinho
    1.32
    iostream
    1.24
     يتيمه
    1.20
     Couture
    1.17
     оригіналу
    0.98
    couts
    0.97
    Activations Density 0.076%

    No Known Activations