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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14599
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and notation related to dimensions and matrices

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

    mathematical notation for matrix dimensions or grid sizes using the "times" symbol.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.88
     propOrder
    -0.70
     ویکی‌پدی
    -0.69
    <unused8>
    -0.64
    <unused23>
    -0.64
    <unused16>
    -0.64
    <unused74>
    -0.64
    <unused79>
    -0.64
    <pad>
    -0.64
    <unused3>
    -0.64
    POSITIVE LOGITS
     bientôt
    0.32
     ProtoMessage
    0.29
     mostrarse
    0.28
    ∬
    0.28
     leitura
    0.28
     Damit
    0.26
    OnError
    0.26
     souligné
    0.26
     combinação
    0.26
     mał
    0.26
    Activations Density 0.297%

    No Known Activations