© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7955
    Prev
    Next
    INDEX
    Explanations

    references to excessive amounts or values, particularly in legal or financial contexts

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

    Exceeding a quantity or boundary

    np_acts-logits-general · gemini-2.0-flash

    exceeding or in excess

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.51
    httphttps
    -0.38
     Fuß
    -0.30
     chaves
    -0.29
     обра
    -0.29
    რი
    -0.29
     gezicht
    -0.28
    footer
    -0.28
     nära
    -0.28
     parede
    -0.28
    POSITIVE LOGITS
     ब्रेकडाउन
    0.64
     exceeding
    0.63
     Over
    0.63
     exceed
    0.59
     (>
    0.59
     exceeds
    0.58
     resourceCulture
    0.58
    Over
    0.58
    OVER
    0.57
    >>>>>>>>
    0.57
    Activations Density 0.340%

    No Known Activations