© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 14693
    Prev
    Next
    INDEX
    Explanations

    updates related to significant events or changes in legal status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iz
    -0.31
     cab
    -0.30
    ↵↵
    -0.30
     le
    -0.29
     monitor
    -0.28
     a
    -0.28
     “
    -0.28
     est
    -0.28
     mix
    -0.28
     edit
    -0.26
    POSITIVE LOGITS
    parsedMessage
    0.93
    expandindo
    0.86
     queſta
    0.85
     يتيمه
    0.81
     noDo
    0.78
    <unused52>
    0.77
    writeFieldEnd
    0.76
    <unused68>
    0.75
    TagMode
    0.75
    <unused8>
    0.75
    Activations Density 0.152%

    No Known Activations