© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 9445
    Prev
    Next
    INDEX
    Explanations

    LaTeX code syntax and structures used for formatting figures and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ist
    -0.35
     is
    -0.31
    -
    -0.29
     only
    -0.27
     also
    -0.27
    ian
    -0.27
     has
    -0.26
    3
    -0.25
    only
    -0.25
    6
    -0.25
    POSITIVE LOGITS
     betweenstory
    1.05
    expandindo
    0.98
     queſta
    0.96
     المعيارى
    0.95
    QMetaType
    0.94
    <unused79>
    0.94
    <unused41>
    0.94
    <unused74>
    0.94
    <unused28>
    0.94
    <unused3>
    0.94
    Activations Density 0.103%

    No Known Activations