© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 402
    Prev
    Next
    INDEX
    Explanations

    structural elements and attributes in markup or programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    structured layout attributes in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    structural brackets and braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.80
    下载附件
    -0.71
    fileID
    -0.69
    ]--;
    -0.65
     LoginPage
    -0.65
     UserDao
    -0.65
     calldata
    -0.64
    WebServlet
    -0.63
     Pliocene
    -0.62
    openha
    -0.61
    POSITIVE LOGITS
     مرئيه
    0.56
     */,
    0.51
    __':
    0.50
    ）、
    0.47
    poons
    0.47
     **/
    0.45
     ویکی‌آمباردا
    0.44
    )),
    0.44
    }}},
    0.43
    }},
    0.43
    Activations Density 0.005%

    No Known Activations