© 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. 28-GEMMASCOPE-RES-16K
    11. 4343
    Prev
    Next
    INDEX
    Explanations

    structured academic or technical content

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

    Text found within HTML tags

    np_acts-logits-general · gemini-2.0-flash

    section titles or formatting

    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
    Билгалдахарш
    -0.88
     للاسماء
    -0.84
    Дереккөздер
    -0.84
    Referanser
    -0.80
    Cyfeiriadau
    -0.79
     nahilalakip
    -0.78
     يتيمه
    -0.77
    లాలు
    -0.75
     gyhoeddwyd
    -0.75
    tanleria
    -0.74
    POSITIVE LOGITS
    <strong>
    0.98
    <h3>
    0.89
    <b>
    0.84
    <h2>
    0.77
    <h4>
    0.68
    <u>
    0.65
    <h1>
    0.63
    <h5>
    0.58
    ###
    0.54
    ##
    0.52
    Activations Density 0.523%

    No Known Activations