© 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. 6353
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal growth and support systems

    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
     queſta
    -1.48
    addPreferred
    -1.39
    出版年
    -1.35
     Chwiliwch
    -1.34
    RenderAtEndOf
    -1.34
     estekak
    -1.32
    rungsseite
    -1.32
    AsNil
    -1.30
     ſind
    -1.30
    ésultats
    -1.30
    POSITIVE LOGITS
     internationally
    -0.01
     nationally
    -0.02
     traditional
    -0.03
     separate
    -0.04
     international
    -0.04
     alongside
    -0.04
     professionally
    -0.04
     residential
    -0.04
     traditionally
    -0.04
     amongst
    -0.04
    Activations Density 4.031%

    No Known Activations