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. 18-GEMMASCOPE-RES-16K
    6. 1178
    Prev
    Next
    INDEX
    Explanations

    terms related to cost and pricing, particularly focusing on expensive and cheap items

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

    low prices and affordability

    np_acts-logits-general · gemini-2.0-flash

    price and cost

    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
     فريبيس
    -0.90
    GEBURTSDATUM
    -0.88
    rungsseite
    -0.76
    abestanden
    -0.74
    SourceChecksum
    -0.72
     بيها
    -0.70
    AndEndTag
    -0.69
     nakalista
    -0.67
    WebElementEntity
    -0.67
     esternos
    -0.65
    POSITIVE LOGITS
     admission
    0.57
     premiums
    0.57
     cost
    0.55
    zuk
    0.55
     dearly
    0.54
     gas
    0.54
     maintenance
    0.53
     rents
    0.52
     rent
    0.52
     solution
    0.52
    Activations Density 0.139%

    No Known Activations