© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5097
    Prev
    Next
    INDEX
    Explanations

    the presence of whitespace characters or blank spaces in the text

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

    Numbers at the beginning of sentences

    np_acts-logits-general · gemini-2.0-flash

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.86
    parsedMessage
    -0.82
    SharedDtor
    -0.81
     للمعارف
    -0.79
    iſchen
    -0.78
    ſammen
    -0.77
    ſelben
    -0.77
    <unused41>
    -0.75
    [@BOS@]
    -0.75
    <pad>
    -0.75
    POSITIVE LOGITS
     special
    0.34
     both
    0.31
     new
    0.30
     non
    0.29
     long
    0.28
    SuppressLint
    0.27
    Empereur
    0.27
     certain
    0.26
     full
    0.25
     personal
    0.25
    Activations Density 0.312%

    No Known Activations