© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4151
    Prev
    Next
    INDEX
    Explanations

    occurrences of document structure commands and LaTeX commands

    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
     or
    -0.48
     vs
    -0.48
     Jaffe
    -0.47
     השני
    -0.44
     або
    -0.44
     puro
    -0.44
    /
    -0.43
    ,
    -0.43
    三位
    -0.42
     extra
    -0.41
    POSITIVE LOGITS
    begin
    2.18
    Begin
    1.16
    BEGIN
    1.16
    存于互联网档案馆
    1.10
    AddTagHelper
    1.08
     begin
    1.08
     viewDidLoad
    1.08
     defaultstate
    1.08
     Begin
    1.06
    تقاوى
    1.04
    Activations Density 0.045%

    No Known Activations