© 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 EvalsExportsAPI 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. 1528
    Prev
    Next
    INDEX
    Explanations

    the presence of curly brace characters, which are commonly used in programming syntax

    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
     above
    -0.53
    ube
    -0.51
     modelAndView
    -0.50
    ือง
    -0.50
    labili
    -0.50
     Christensen
    -0.49
     beyond
    -0.48
    laient
    -0.48
    یه
    -0.47
    fog
    -0.47
    POSITIVE LOGITS
    __":
    1.10
    __":
    1.06
    "])){
    1.04
    EndGlobalSection
    1.01
    __':
    1.00
    MigrationBuilder
    0.95
    '])){
    0.94
    ")){
    0.93
    ))){
    0.93
    --){
    0.91
    Activations Density 0.081%

    No Known Activations