© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 14231
    Prev
    Next
    INDEX
    Explanations

    standard input and output stream commands in C++

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     loài
    -0.61
    起
    -0.60
    +#+#
    -0.60
    有
    -0.59
     mezz
    -0.57
     dip
    -0.56
     hammer
    -0.56
     knock
    -0.55
    爪
    -0.55
    Yon
    -0.55
    POSITIVE LOGITS
    Cout
    1.34
     cout
    1.33
    cout
    1.30
     Cout
    1.27
     يتيمه
    1.17
     Couture
    1.10
    iostream
    1.07
     Coutinho
    1.04
     оригіналу
    1.01
    ImageContext
    0.94
    Activations Density 0.044%

    No Known Activations