© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6721
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms related to equations and functions

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

    Mathematical or scientific notation with "alpha"

    np_acts-logits-general · gemini-2.0-flash

    greek letters and numbers

    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
    transQ
    -0.61
    interopRequire
    -0.60
    tagHelperRunner
    -0.60
    #+#
    -0.59
     kasarigan
    -0.59
    ArgsConstructor
    -0.58
    ſelf
    -0.56
    PerformLayout
    -0.54
     crossorigin
    -0.53
    writeFieldEnd
    -0.52
    POSITIVE LOGITS
     enseignants
    0.36
     Cleanser
    0.36
    Display
    0.33
    Географи
    0.33
     nearer
    0.32
    offsetTop
    0.32
    uesas
    0.32
    ANCEL
    0.32
     متحده
    0.32
    Salu
    0.32
    Activations Density 1.954%

    No Known Activations