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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 587
    Prev
    Next
    INDEX
    Explanations

    food items, particularly those related to sandwiches and meat products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.80
    IBarButtonItem
    -0.79
    LookAnd
    -0.79
    GEBURTSDATUM
    -0.78
    tagHelperRunner
    -0.76
    complexContent
    -0.75
     nahilalakip
    -0.73
    Koordinaten
    -0.73
    MigrationBuilder
    -0.70
    دانشنامهٔ
    -0.70
    POSITIVE LOGITS
     cheese
    1.01
     sausage
    0.90
     Cheese
    0.88
    ciutto
    0.82
    Cheese
    0.81
     meat
    0.81
     cheeses
    0.80
     Sausage
    0.79
    cheese
    0.77
     bacon
    0.73
    Activations Density 0.648%

    No Known Activations