© 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. 6309
    Prev
    Next
    INDEX
    Explanations

    references to types of food and cooking methods

    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
    rungsseite
    -0.43
    SharedCtor
    -0.43
    mobileqq
    -0.41
    gemeester
    -0.41
     Walkover
    -0.41
     Chwiliwch
    -0.40
    writeFieldEnd
    -0.39
    <?
    -0.39
     infanti
    -0.39
     réflex
    -0.38
    POSITIVE LOGITS
     bread
    1.36
     Bread
    1.15
     breads
    1.07
    Bread
    1.03
    bread
    1.01
     baguette
    1.01
    🍞
    0.99
     loaves
    0.98
     loaf
    0.96
     BREAD
    0.96
    Activations Density 0.195%

    No Known Activations