© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 13788
    Prev
    Next
    INDEX
    Explanations

    references or sections dedicated to bibliographies in texts

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

    bibliography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Algemeen
    -0.43
    дневно
    -0.42
     bezeichneter
    -0.41
     daytime
    -0.40
     ​​
    -0.40
    askin
    -0.40
    care
    -0.38
     Workers
    -0.38
    *(
    -0.38
    act
    -0.37
    POSITIVE LOGITS
     bibliography
    2.11
     Bibliography
    1.81
    bibliography
    1.67
     bibliographic
    1.66
    Bibliography
    1.62
     bibliographical
    1.59
     Bibli
    1.55
     bibli
    1.55
     bibliographies
    1.52
    bibli
    1.43
    Activations Density 0.014%

    No Known Activations