© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11640
    Prev
    Next
    INDEX
    Explanations

    terms related to food and dietary habits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CGRectMake
    -0.41
    irem
    -0.40
    ıklı
    -0.40
    RTSC
    -0.40
    awaiter
    -0.39
    MessageTagHelper
    -0.39
    TokenNameDOT
    -0.38
     Administrativna
    -0.38
    ceta
    -0.37
     Biôgrafia
    -0.37
    POSITIVE LOGITS
    stuff
    0.72
     stuffs
    0.65
    stuffs
    0.63
    Food
    0.55
     Food
    0.55
    courts
    0.52
     FOOD
    0.51
    grains
    0.50
    aarrggbb
    0.49
    KommentareTeilen
    0.48
    Activations Density 0.118%

    No Known Activations