© 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. 7361
    Prev
    Next
    INDEX
    Explanations

    mathematical or statistical formatting and expressions

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

    Numbers followed by arithmetic operations, or percentages

    np_acts-logits-general · gemini-2.0-flash

    numbers and symbols

    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
    LookAnd
    -0.81
     AssemblyCulture
    -0.77
    AnimationsModule
    -0.74
    MessageTagHelper
    -0.69
    errHandler
    -0.67
     propOrder
    -0.64
     wireType
    -0.63
     utafitiHapana
    -0.62
     getItemId
    -0.61
     ब्रेकडाउन
    -0.60
    POSITIVE LOGITS
     twenty
    0.46
    toJson
    0.43
     zama
    0.40
     Zagreb
    0.39
    twenty
    0.39
    zat
    0.39
    zac
    0.39
     Twenty
    0.38
    作文
    0.38
     Zav
    0.38
    Activations Density 1.537%

    No Known Activations