© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 80364
    Prev
    Next
    INDEX
    Explanations

    JavaScript syntax for function definitions, particularly utilizing arrow functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    data label and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //~
    -0.49
     imageNamed
    -0.45
     Halen
    -0.43
    躇
    -0.43
    pshots
    -0.43
     rowspan
    -0.41
    nium
    -0.41
     dilation
    -0.41
     \
    -0.41
    \/
    -0.41
    POSITIVE LOGITS
    =>{
    1.06
    (()=>{
    1.03
    )=>{
    0.99
     ()=>{
    0.96
    ()=>{
    0.88
    =()=>{
    0.84
    ':{
    0.75
    ":{
    0.75
     =>{
    0.71
    ==""){
    0.70
    Activations Density 0.007%

    No Known Activations