© 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. 3-GEMMASCOPE-RES-16K
    6. 6934
    Prev
    Next
    INDEX
    Explanations

    technical components and keywords related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]}
    -0.68
     سكانية
    -0.59
     "'");
    -0.59
    ']]
    -0.56
    )}</
    -0.56
     }}}{
    -0.54
    ()};
    -0.54
    "]];
    -0.54
    ()}}
    -0.53
     "'";
    -0.53
    POSITIVE LOGITS
    ButterKnife
    0.82
    UrlResolution
    0.73
    Portale
    0.72
    aarrggbb
    0.68
    ArgsConstructor
    0.67
     MonoBehaviour
    0.66
    TagMode
    0.66
    makeText
    0.66
    msgSender
    0.65
    TextWatcher
    0.65
    Activations Density 0.019%

    No Known Activations