© 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. 35-GEMMASCOPE-RES-16K
    11. 7369
    Prev
    Next
    INDEX
    Explanations

    conclusions or statements of result at the end of discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.69
     &___
    -0.48
     iprot
    -0.46
    parsedMessage
    -0.45
    ItemBackground
    -0.45
    Хьажоргаш
    -0.43
    Rüyada
    -0.43
     Roskov
    -0.42
    Personensuche
    -0.42
    adaptiveStyles
    -0.41
    POSITIVE LOGITS
     however
    3.64
    however
    2.84
     However
    2.83
    However
    2.75
     entanto
    2.58
     però
    2.47
     cependant
    2.44
     tuttavia
    2.44
     jedoch
    2.42
     однако
    2.39
    Activations Density 1.018%

    No Known Activations