© 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. 35-GEMMASCOPE-RES-16K
    11. 15294
    Prev
    Next
    INDEX
    Explanations

    quantitative terms and mathematical expressions related to probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.48
     يتيمه
    -0.47
    ViewImports
    -0.44
     Мексичка
    -0.38
    aderas
    -0.35
     Grüsse
    -0.34
    ọt
    -0.33
    Viki
    -0.33
    ushin
    -0.33
    //
    -0.33
    POSITIVE LOGITS
     probability
    2.11
     probabilities
    1.92
     Probability
    1.84
    probability
    1.72
    Probability
    1.71
     Probab
    1.66
     probab
    1.63
     probabilidad
    1.51
    概率
    1.51
    Probab
    1.46
    Activations Density 2.209%

    No Known Activations