© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 6415
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as function definitions, conditionals, and assertions

    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
    runOnUiThread
    -0.32
    strcat
    -0.31
    jScrollPane
    -0.30
    รอบ
    -0.28
     pol
    -0.28
    sendRedirect
    -0.28
    aVar
    -0.27
    ToListAsync
    -0.27
    []
    -0.27
     instead
    -0.26
    POSITIVE LOGITS
    assert
    1.38
     assert
    1.20
    Assert
    1.08
     Assert
    1.03
    ASSERT
    1.03
     assurance
    1.03
     assure
    1.02
     assurances
    1.01
     asserts
    1.01
     assertions
    0.96
    Activations Density 0.352%

    No Known Activations