© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14045
    Prev
    Next
    INDEX
    Explanations

    specific formatting elements, references, and structural components in texts

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

    Mathematical or scientific notation

    np_acts-logits-general · gemini-2.0-flash

    # followed by number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.62
     INVENTION
    -0.55
    +#+
    -0.55
    DotNetBar
    -0.51
     Photocase
    -0.51
    Rohy
    -0.50
     AssemblyCompany
    -0.49
    󠁴
    -0.49
    simpleType
    -0.49
    AnchorStyles
    -0.49
    POSITIVE LOGITS
    uxxxx
    1.43
    weightedMode
    0.81
    InjectAttribute
    0.66
    numeros
    0.52
     MemoryStream
    0.48
     ORGANISM
    0.43
    IUrlHelper
    0.35
     editText
    0.33
    __':
    0.32
     wobec
    0.31
    Activations Density 0.228%

    No Known Activations