© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2731
    Prev
    Next
    INDEX
    Explanations

    references to scientific or academic materials

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

    "(#...){ref-type="supplementary-material"}"

    np_acts-logits-general · gemini-2.0-flash

    supplementary-material references

    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
     дописавши
    -0.54
     estekak
    -0.52
     Redewendung
    -0.51
    CPtr
    -0.51
    Bakgrunnsstoff
    -0.49
    ValueStyle
    -0.49
     ditangkap
    -0.46
     Nachweis
    -0.46
    ցված
    -0.46
    expandindo
    -0.46
    POSITIVE LOGITS
    material
    2.70
     material
    2.23
     Material
    2.14
    Material
    2.14
     MATERIAL
    2.00
    MATERIAL
    1.95
     materiale
    1.52
    aterial
    1.35
     materialize
    1.27
     materiaal
    1.24
    Activations Density 0.046%

    No Known Activations