© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 3480
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific analysis and formulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.66
     nakalista
    -0.65
     NSCoder
    -0.63
     CreateTagHelper
    -0.61
     оригіналу
    -0.60
    +#+#
    -0.58
     noDo
    -0.55
    ivably
    -0.53
     begitu
    -0.52
     AssemblyProduct
    -0.51
    POSITIVE LOGITS
    //
    0.55
    saraba
    0.53
     članak
    0.52
     AppBar
    0.51
    今度は
    0.51
     forState
    0.51
    мули
    0.49
    alpin
    0.48
    ServiceModel
    0.47
    Olvid
    0.46
    Activations Density 0.668%

    No Known Activations