© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6974
    Prev
    Next
    INDEX
    Explanations

    keywords related to tax and financial documentation

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

    Comes after currency symbols, punctuation, or math symbols

    np_acts-logits-general · gemini-2.0-flash

    potential outcomes

    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
     HasFactory
    -0.64
    RenderAtEndOf
    -0.59
     visse
    -0.56
     FetchType
    -0.53
     democrática
    -0.51
     Changelog
    -0.51
     Ensign
    -0.51
     régionale
    -0.50
    الدراسه
    -0.48
     défaut
    -0.48
    POSITIVE LOGITS
     customized
    0.91
     custom
    0.88
     services
    0.81
     tailored
    0.76
     specializes
    0.76
     bespoke
    0.76
     consultations
    0.76
     Custom
    0.75
     specializing
    0.73
     consultation
    0.73
    Activations Density 0.160%

    No Known Activations