© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 7221
    Prev
    Next
    INDEX
    Explanations

    instances of specific terms related to legal cases and their proceedings

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

    Preceding numbers, symbols, or punctuation

    np_acts-logits-general · gemini-2.0-flash

    quality and price evaluations

    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
    exitRule
    -0.67
     BoxFit
    -0.67
     pinulongan
    -0.63
    Personendaten
    -0.61
     précie
    -0.58
    WebControls
    -0.58
     fortemente
    -0.56
     onPostExecute
    -0.56
     kasarigan
    -0.56
    DockStyle
    -0.55
    POSITIVE LOGITS
     workmanship
    0.83
     prices
    0.81
     overall
    0.77
     quality
    0.74
     price
    0.71
    何より
    0.65
    overall
    0.65
     worst
    0.64
     craftsmanship
    0.62
    worst
    0.62
    Activations Density 0.158%

    No Known Activations