© 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. 2-GEMMASCOPE-RES-16K
    11. 4385
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements and lengths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bewußt
    -0.63
     Schluß
    -0.56
    قایناق‌لار
    -0.52
    Parcelize
    -0.49
     InputDecoration
    -0.46
    istoitu
    -0.45
    页面存档备份
    -0.45
     Einfluß
    -0.45
     didalam
    -0.43
     např
    -0.43
    POSITIVE LOGITS
    󠁿
    0.59
    s
    0.57
     CanadaChoose
    0.55
     
    0.51
    ädie
    0.50
     kohdetta
    0.49
    цезда
    0.48
    vetrain
    0.47
    ietal
    0.47
    mpotent
    0.47
    Activations Density 0.818%

    No Known Activations