© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28168
    Prev
    Next
    INDEX
    Explanations

    sports statistics and performance metrics

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

    goals, games, and scoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ApiException
    -0.64
    TagHelpers
    -0.56
     Picchu
    -0.55
     TestBed
    -0.54
    waar
    -0.54
    MLLoader
    -0.53
    forRoot
    -0.52
    kuun
    -0.52
     préférence
    -0.52
    ceton
    -0.52
    POSITIVE LOGITS
     الحره
    0.59
    OGND
    0.55
    setVerticalGroup
    0.55
    OrBuilder
    0.54
     Roskov
    0.54
     onCreateView
    0.51
    ...@
    0.49
    ()){
    
    0.49
    SqlParameter
    0.49
    ")){
    0.48
    Activations Density 0.140%

    No Known Activations