© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4935
    Prev
    Next
    INDEX
    Explanations

    specialized formatting or symbols related to mathematical or scientific expressions

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

    MathML, LaTeX, or code snippets

    np_acts-logits-general · gemini-2.0-flash

    latex math commands

    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
    ///</
    -0.38
     שיש
    -0.36
    Дереккөздер
    -0.36
    ('*',
    -0.35
    drawSprites
    -0.35
     Italijanski
    -0.35
     Rücks
    -0.34
    )))),
    -0.33
    (":");
    -0.33
    ("*");
    -0.32
    POSITIVE LOGITS
    httphttps
    0.66
     ſta
    0.65
     CreateTagHelper
    0.65
     referrerpolicy
    0.64
    aarrggbb
    0.63
    enumii
    0.61
    ſelf
    0.61
     myſelf
    0.60
     dentaire
    0.60
     leaſt
    0.60
    Activations Density 0.082%

    No Known Activations