© 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. 28-GEMMASCOPE-RES-16K
    11. 9469
    Prev
    Next
    INDEX
    Explanations

    references to the creation and posting of content

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

    "Created by" in file headers

    np_acts-logits-general · gemini-2.0-flash

    code creation comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Estatal
    -0.34
    forChild
    -0.31
    драт
    -0.31
    herzog
    -0.31
     scant
    -0.30
    #
    -0.30
    anium
    -0.30
     ModelExpression
    -0.30
     فريبيس
    -0.29
    tagena
    -0.29
    POSITIVE LOGITS
    AndEndTag
    0.75
    RenderAtEndOf
    0.68
    AddTagHelper
    0.62
     propOrder
    0.59
    aarrggbb
    0.58
    substance
    0.54
     surla
    0.52
    tvguidetime
    0.52
    DockStyle
    0.51
    IBarButtonItem
    0.51
    Activations Density 0.036%

    No Known Activations