© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3694
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases associated with describing, outlining, illustrating, and explaining concepts or ideas

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

    explanations or descriptions

    np_acts-logits-general · gemini-2.0-flash

    explaining how or why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.65
     насељу
    -0.59
    sbericht
    -0.54
     noDo
    -0.52
     Italijanski
    -0.52
     Audiodateien
    -0.51
     parlour
    -0.47
    دانشنامهٔ
    -0.47
    andidates
    -0.46
    perator
    -0.46
    POSITIVE LOGITS
     how
    1.14
     why
    0.71
    how
    0.70
     cómo
    0.67
     what
    0.66
     bagaimana
    0.66
     hvordan
    0.54
     كيف
    0.54
     nasıl
    0.51
     whether
    0.50
    Activations Density 0.672%

    No Known Activations