© 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. 1875
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and concepts related to biological structures and their functions

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

    Word before chemical elements or organisms

    np_acts-logits-general · gemini-2.0-flash

    biological entities and cells

    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
    Enllaços
    -0.41
    requireNonNull
    -0.36
    Anch
    -0.34
    <eos>
    -0.33
    FlowLayout
    -0.33
    arXiv
    -0.32
    amarin
    -0.32
    Fordítás
    -0.32
    protoimpl
    -0.32
    BindingSource
    -0.31
    POSITIVE LOGITS
    новништво
    0.62
     whoſe
    0.51
    gameserver
    0.51
    rapie
    0.49
    RTHOOK
    0.49
     linho
    0.49
     فريبيس
    0.49
     Italijanski
    0.48
    出版年
    0.48
    <?
    0.47
    Activations Density 1.966%

    No Known Activations