© 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. 8531
    Prev
    Next
    INDEX
    Explanations

    references to companies and organizations in legal and corporate contexts

    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
    []);
    -0.59
     Wiesen
    -0.52
     Arial
    -0.51
    ()].
    -0.50
    ')['
    -0.49
     '-';
    -0.49
     spot
    -0.48
     igen
    -0.48
     ویکی‌پدیای
    -0.48
     Exactos
    -0.47
    POSITIVE LOGITS
     Ltd
    1.20
     LLC
    1.12
     Inc
    1.07
    Ltd
    1.03
     LTD
    0.98
     Bhd
    0.98
    DoubleQuotes
    0.98
    有限公司
    0.92
     ltd
    0.90
    LTD
    0.90
    Activations Density 0.126%

    No Known Activations