© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8456
    Prev
    Next
    INDEX
    Explanations

    references to statistical or mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     électronique
    -0.39
    دانشنامهٔ
    -0.34
     kanya
    -0.34
     IOError
    -0.33
    multicolumn
    -0.32
     godz
    -0.31
     Upper
    -0.31
     typhoon
    -0.31
     Senat
    -0.30
    StatusBadRequest
    -0.30
    POSITIVE LOGITS
     resourceCulture
    0.78
     invokingState
    0.69
    الحياه
    0.68
    HtmlAttribute
    0.68
     autorytatywna
    0.66
     CreateTagHelper
    0.64
    Personendaten
    0.63
    帖最后由
    0.62
    NegativeButton
    0.62
    Autoritní
    0.61
    Activations Density 0.034%

    No Known Activations