© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 12376
    Prev
    Next
    INDEX
    Explanations

    references to chicken in various forms and preparations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gem
    -0.82
    Lith
    -0.79
     Lith
    -0.78
    stalt
    -0.77
    PreferredItem
    -0.77
    ρώ
    -0.75
     mapper
    -0.74
     Heist
    -0.74
    Personensuche
    -0.74
    Roh
    -0.73
    POSITIVE LOGITS
     Chicken
    1.93
     chicken
    1.92
    Chicken
    1.70
    chicken
    1.68
     CHICKEN
    1.66
     chickens
    1.56
     Chickens
    1.40
    ICKEN
    1.05
     poulet
    1.04
    鸡
    0.99
    Activations Density 0.079%

    No Known Activations