© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 852
    Prev
    Next
    INDEX
    Explanations

    terms related to food, particularly salad ingredients and dressings

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

    Salad dressings, oils, and accompaniments

    np_acts-logits-general · gemini-2.0-flash

    salad dressing ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Priorities
    -0.45
     Katzen
    -0.45
    submit
    -0.45
    getRuntime
    -0.44
    anthrene
    -0.43
     Priority
    -0.42
    Priorities
    -0.42
    XmlSchema
    -0.42
    heureux
    -0.41
     catto
    -0.41
    POSITIVE LOGITS
     dressing
    1.36
     Dressing
    1.28
    Dressing
    1.15
    dressing
    1.09
     dressings
    1.09
     vinaigrette
    1.07
     salads
    0.94
     Salad
    0.94
    Salad
    0.91
     DRESS
    0.90
    Activations Density 0.183%

    No Known Activations