© 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. 40-GEMMASCOPE-RES-16K
    6. 5002
    Prev
    Next
    INDEX
    Explanations

    specific roles or titles associated with people in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addGap
    -0.52
     gyhoeddwyd
    -0.46
     Paglinawan
    -0.46
    addPreferredGap
    -0.45
    delwed
    -0.44
    Diweddarwch
    -0.44
    Tributes
    -0.43
    szönöm
    -0.42
     Theſe
    -0.41
     Adds
    -0.39
    POSITIVE LOGITS
     told
    2.23
    told
    1.52
     Told
    1.31
    Told
    1.23
     tells
    0.99
     tell
    0.96
    告诉
    0.92
    告訴
    0.91
     telling
    0.88
    Tell
    0.84
    Activations Density 0.261%

    No Known Activations