© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 7206
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to high costs or expenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seeder
    -0.72
     فريبيس
    -0.69
     oprot
    -0.67
    utnant
    -0.63
    Slf
    -0.62
    Personendaten
    -0.62
     Jordi
    -0.59
    lossians
    -0.58
     dépos
    -0.58
     répartition
    -0.58
    POSITIVE LOGITS
     expensive
    3.04
     Expensive
    2.73
    expensive
    2.72
    Expensive
    2.57
     pricey
    2.25
     costly
    2.23
     дорого
    1.60
     overpriced
    1.60
     caros
    1.54
     teuer
    1.45
    Activations Density 0.062%

    No Known Activations