© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1593
    Prev
    Next
    INDEX
    Explanations

    concepts related to language and communication

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

    Linguistics and language-related terms

    np_acts-logits-general · gemini-2.0-flash

    language and linguistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.54
    Искәрмәләр
    -0.52
    таратура
    -0.50
    fastjson
    -0.49
    findpost
    -0.49
    +#+#
    -0.48
    __);
    -0.48
     ddelweddau
    -0.47
     للمعارف
    -0.47
     Biôgrafia
    -0.47
    POSITIVE LOGITS
     linguistics
    0.62
     linguistic
    0.62
     grammatical
    0.61
     lingü
    0.57
     Linguistics
    0.57
    olingo
    0.54
     grammar
    0.53
     linguistique
    0.52
     language
    0.52
    Lingu
    0.51
    Activations Density 0.782%

    No Known Activations