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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10738
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and structural components in formal mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.94
     setEmail
    -0.84
     $_"
    -0.82
    <unused43>
    -0.81
    <unused41>
    -0.81
    <unused16>
    -0.81
    <pad>
    -0.81
    <unused17>
    -0.81
    <unused14>
    -0.81
    <unused8>
    -0.81
    POSITIVE LOGITS
     and
    0.35
    ↵↵
    0.28
     و
    0.26
    ↵
    0.25
     or
    0.25
    Q
    0.24
     imaginar
    0.24
     عملی
    0.24
     und
    0.24
     uska
    0.24
    Activations Density 1.454%

    No Known Activations