© 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-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 11066
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Andersen."

    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
    呼ば
    -0.71
    一緒に
    -0.71
    言い
    -0.59
    共に
    -0.52
    考え
    -0.52
    思い
    -0.51
    其他
    -0.49
    EndProject
    -0.47
    その
    -0.47
    ともに
    -0.45
    POSITIVE LOGITS
     zwar
    0.62
    RetentionPolicy
    0.52
    amento
    0.52
    And
    0.51
    EReference
    0.48
     
    0.47
     ویکی‌پدی
    0.46
    Beyond
    0.45
    AndEndTag
    0.45
    脚注の使い方
    0.45
    Activations Density 0.295%

    No Known Activations