© 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. 4909
    Prev
    Next
    INDEX
    Explanations

    terms related to outsourcing or externalization of tasks or resources

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

    Followed by unusual two-or-three letter strings

    np_acts-logits-general · gemini-2.0-flash

    unsung heroes

    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
    tal
    -0.86
    the
    -0.81
    tttt
    -0.71
    tre
    -0.70
    tra
    -0.69
    to
    -0.69
    t
    -0.68
    tar
    -0.68
    tri
    -0.68
    tro
    -0.67
    POSITIVE LOGITS
     متعلقه
    0.42
     ujednoznacz
    0.42
    ing
    0.38
    draft
    0.38
    bells
    0.38
    ted
    0.37
    λοι
    0.36
    SEGUIR
    0.35
    os
    0.34
    ISupport
    0.34
    Activations Density 0.399%

    No Known Activations