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

    Neuronpedia

    Jacobian LensNEW
    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. 9848
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and special formatting cues in the text

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

    Numbers, especially years

    np_acts-logits-general · gemini-2.0-flash

    numbers and dates

    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
     ModelExpression
    -0.75
    openzeppelin
    -0.74
    tagHelperRunner
    -0.73
    AndEndTag
    -0.70
    ValueStyle
    -0.68
    GOTREF
    -0.64
    XmlAccessorType
    -0.61
    parsedMessage
    -0.61
    fromnode
    -0.60
    出版年
    -0.59
    POSITIVE LOGITS
     /
    0.36
     छोड़
    0.31
    قایناق‌لار
    0.29
    double
    0.28
    mu
    0.28
     Haftung
    0.27
     malheur
    0.27
    BeginContext
    0.27
     s
    0.27
     peuple
    0.26
    Activations Density 0.088%

    No Known Activations