© 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. 3463
    Prev
    Next
    INDEX
    Explanations

    Arabic characters and numerals, with a particular focus on their structural elements

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

    Right-to-left languages or symbols

    np_acts-logits-general · gemini-2.0-flash

    Jabal Omar

    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
     Sosial
    -0.40
     ourselves
    -0.39
    Билгалдахарш
    -0.38
     myself
    -0.36
    estacks
    -0.36
     origines
    -0.36
     “[
    -0.35
     sosial
    -0.35
    anglès
    -0.34
     newest
    -0.33
    POSITIVE LOGITS
    featureID
    0.60
     EconPapers
    0.59
     AsyncTask
    0.55
     ProtoMessage
    0.52
    出版年
    0.52
     FetchType
    0.52
    <?
    0.50
    URLException
    0.50
     لينك
    0.49
    حياته
    0.49
    Activations Density 0.002%

    No Known Activations