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

    Neuronpedia

    Jacobian LensNEW
    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 - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1496
    Prev
    Next
    INDEX
    Explanations

    the presence of specific structural markers in a document, particularly those indicating the beginning of sections or form elements

    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
    ↵↵
    -0.78
    ↵
    -0.69
    ).
    -0.55
    ].
    -0.54
     nakalista
    -0.54
    ]),
    -0.47
    .
    -0.46
    ]).
    -0.44
    )}>
    -0.44
    .”
    -0.44
    POSITIVE LOGITS
     nahilalakip
    1.01
     Signalez
    0.96
     NDEBUG
    0.90
     ویکی‌پدیای
    0.85
    تقاوى
    0.84
    EndInit
    0.84
     pinulongan
    0.81
    AnimationsModule
    0.79
     Мексичка
    0.77
     ivelany
    0.73
    Activations Density 0.616%

    No Known Activations