© 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. 24-GEMMASCOPE-RES-16K
    11. 1176
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving negative values or certain variables

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

    Superscripted indices with mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    numbers or variables after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    ſelf
    -0.56
    InSection
    -0.51
     pleaſure
    -0.49
     Inſ
    -0.48
     Majefty
    -0.47
     itſelf
    -0.47
     Perſ
    -0.46
     themſelves
    -0.46
    httphttps
    -0.45
     Conſ
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.52
     bénévol
    0.45
    ]-'
    0.44
     subtract
    0.42
     Mahl
    0.42
     utafitiHapana
    0.41
    FunctionFlags
    0.39
     Subtract
    0.39
    hyrchwyd
    0.38
     subtracted
    0.38
    Activations Density 1.189%

    No Known Activations