© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2610
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to various scientific fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $
    -0.53
     sold
    -0.48
     seien
    -0.48
     ex
    -0.47
     three
    -0.45
     so
    -0.44
     him
    -0.44
     by
    -0.44
     He
    -0.43
    ोड़
    -0.42
    POSITIVE LOGITS
    VersionUID
    1.03
     CreateTagHelper
    1.01
    DataAnnotations
    0.97
     MainAxisSize
    0.95
     AssemblyCompany
    0.94
    帖最后由
    0.92
    AndEndTag
    0.92
    WaitGroup
    0.89
     himo
    0.89
    tvguidetime
    0.87
    Activations Density 3.404%

    No Known Activations