© 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. 3-GEMMASCOPE-RES-16K
    11. 4831
    Prev
    Next
    INDEX
    Explanations

    various syntax and formatting elements in code or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.60
    A
    -0.59
    x
    -0.59
    0
    -0.57
    1
    -0.56
    2
    -0.54
    3
    -0.54
    (
    -0.53
    h
    -0.52
    L
    -0.52
    POSITIVE LOGITS
    <unused68>
    1.05
    <unused52>
    1.05
    [@BOS@]
    1.05
    <unused14>
    1.05
    <unused79>
    1.05
    <unused28>
    1.05
    <unused47>
    1.05
    <unused3>
    1.05
    <unused74>
    1.05
    <unused8>
    1.04
    Activations Density 1.285%

    No Known Activations