© 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. 24-GEMMASCOPE-RES-16K
    11. 1859
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "with" in various contexts

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

    "With respect/regard/reference" phrases

    np_acts-logits-general · gemini-2.0-flash

    regarding specific points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     infatti
    -0.67
    ../../../
    -0.57
    ながら
    -0.56
     manqué
    -0.56
    TagMode
    -0.52
     though
    -0.51
    िखित
    -0.51
     czyli
    -0.49
     inoltre
    -0.49
     gewesen
    -0.47
    POSITIVE LOGITS
     regard
    1.65
     regards
    1.59
     respect
    1.55
    stood
    1.20
    regard
    1.19
    standing
    1.15
    respect
    1.12
    drawn
    1.07
     impunity
    1.05
    regards
    1.05
    Activations Density 0.444%

    No Known Activations