Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13804
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to scientific studies and materials

    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
     autorytatywna
    -0.70
    VIAF
    -0.66
     ویکی‌پدی
    -0.64
    });*/
    -0.63
     Ause
    -0.58
    ."));
    -0.57
    Népesség
    -0.56
     سكانية
    -0.56
    yelidikan
    -0.55
     okuyayım
    -0.55
    POSITIVE LOGITS
    AtIndexPath
    0.61
    TextBoxColumn
    0.47
    tected
    0.46
     depending
    0.46
     varies
    0.45
     correctes
    0.44
     depends
    0.42
     enz
    0.42
     बाद
    0.42
    PointCloud
    0.42
    Activations Density 0.994%

    No Known Activations