Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16140
    Prev
    Next
    INDEX
    Explanations

    mentions of buffet-style dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or technical text

    np_acts-logits-general · gemini-2.0-flash

    buffet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.54
    
    -0.48
    脚注の使い方
    -0.48
    Хьажоргаш
    -0.48
     informée
    -0.47
    homonymie
    -0.46
    reportWebVitals
    -0.44
     CanadaChoose
    -0.44
    izr
    -0.44
    enumii
    -0.44
    POSITIVE LOGITS
     buffet
    1.56
     Buffet
    1.34
    buffet
    1.23
    Buff
    1.21
     buff
    1.16
     BUFF
    1.07
     Buff
    1.02
     buf
    0.94
    buff
    0.94
    BUFF
    0.88
    Activations Density 0.053%

    No Known Activations