Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12836
    Prev
    Next
    INDEX
    Explanations

    JSON objects and their structure

    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
    DockStyle
    -0.72
    extAlignment
    -0.60
    日閲覧
    -0.56
    awtextra
    -0.56
     concor
    -0.56
    thâu
    -0.54
    ériale
    -0.54
     womb
    -0.54
     recla
    -0.53
    脚注の使い方
    -0.53
    POSITIVE LOGITS
     <>",
    0.77
     [{
    0.76
    ":[{
    0.71
     [{
    
    0.68
     aload
    0.67
    transQ
    0.67
    },{
    
    0.61
    ([{
    0.60
    Autowired
    0.59
    ########.
    0.58
    Activations Density 0.128%

    No Known Activations