© 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. 9937
    Prev
    Next
    INDEX
    Explanations

    terms related to legal disclaimers and warranties

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

    Followed by comma and a logical connector

    np_acts-logits-general · gemini-2.0-flash

    implies logical consequence

    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
     ligiloj
    -0.93
     CreateTagHelper
    -0.83
     JpaRepository
    -0.76
    utives
    -0.75
     Efq
    -0.72
    각주
    -0.72
     ―――――
    -0.71
     GoogleFonts
    -0.71
    actéristique
    -0.70
     Theſe
    -0.70
    POSITIVE LOGITS
     so
    2.15
     therefore
    2.06
    所以
    1.95
     поэтому
    1.91
     Therefore
    1.85
    Therefore
    1.80
     nên
    1.79
     hence
    1.77
     所以
    1.70
     donc
    1.68
    Activations Density 1.697%

    No Known Activations