© 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. 30-GEMMASCOPE-RES-16K
    11. 10929
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and syntax elements

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

    Characters, symbols, and numbers

    np_acts-logits-general · gemini-2.0-flash

    currency symbols and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -0.57
     defStyleAttr
    -0.48
     тогда
    -0.47
     alors
    -0.47
     Тогда
    -0.46
     wtedy
    -0.45
     Then
    -0.44
    bottomRight
    -0.44
    Then
    -0.44
    DriverManager
    -0.43
    POSITIVE LOGITS
     navideña
    0.46
     makeStyles
    0.41
     literario
    0.39
     navideño
    0.38
     Meksiku
    0.38
    jeuner
    0.37
     lectores
    0.37
     jScrollPane
    0.37
     Japón
    0.37
     JADX
    0.36
    Activations Density 0.211%

    No Known Activations