© 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. 24-GEMMASCOPE-RES-16K
    11. 10308
    Prev
    Next
    INDEX
    Explanations

    elements related to technical specifications or performance metrics

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

    Follows question words, "is", "has"

    np_acts-logits-general · gemini-2.0-flash

    political party violate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.47
    mappedBy
    -0.37
    principalTable
    -0.36
    GOTREF
    -0.35
     additionally
    -0.34
     suffix
    -0.34
    Uninitialized
    -0.34
     requesting
    -0.33
     Iter
    -0.32
    chaffenheit
    -0.32
    POSITIVE LOGITS
     autorytatywna
    0.71
    也算是
    0.52
    ]")]
    0.52
    튿
    0.51
    JspWriter
    0.50
     MenuView
    0.49
     przecież
    0.48
    Географиясе
    0.48
     vectorielles
    0.48
    也算
    0.47
    Activations Density 0.761%

    No Known Activations