© 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. 14107
    Prev
    Next
    INDEX
    Explanations

    numerical references and counts related to episodes, seasons, or chapters

    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
    第二次
    -0.37
    eseorang
    -0.35
    existing
    -0.35
    anskje
    -0.35
     Reverso
    -0.35
    ledem
    -0.34
     răsp
    -0.34
     tempor
    -0.32
    recent
    -0.32
    براير
    -0.32
    POSITIVE LOGITS
     seven
    0.85
     five
    0.85
     six
    0.84
     three
    0.84
     four
    0.81
     nine
    0.80
     eight
    0.80
     two
    0.79
     one
    0.73
     eleven
    0.64
    Activations Density 1.064%

    No Known Activations