© 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. 11627
    Prev
    Next
    INDEX
    Explanations

    references to letters and editorials in publications

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

    "Letters" or "editor" appearing in text

    np_acts-logits-general · gemini-2.0-flash

    Letters to the editor

    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
     péri
    -0.48
     MainAxisSize
    -0.41
     noOf
    -0.40
    oraus
    -0.40
    registrer
    -0.39
     Usaha
    -0.38
    Lycka
    -0.38
     مشين
    -0.38
     beliau
    -0.36
    prender
    -0.36
    POSITIVE LOGITS
     Letters
    0.76
    Letters
    0.73
    letters
    0.65
     LETTERS
    0.63
     letters
    0.63
     CURIAM
    0.62
    LETTERS
    0.55
    tonode
    0.54
    BufferException
    0.53
    verwijspagina
    0.52
    Activations Density 0.424%

    No Known Activations