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. 2-GEMMASCOPE-RES-16K
    6. 6726
    Prev
    Next
    INDEX
    Explanations

    names and titles associated with research or academic work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    جمعیت
    -0.51
    Coordenadas
    -0.48
     prati
    -0.47
     vẽ
    -0.46
     difference
    -0.44
    zędu
    -0.44
    exif
    -0.43
    onomia
    -0.43
     again
    -0.42
     Antibodies
    -0.42
    POSITIVE LOGITS
    ts
    1.20
    AndEndTag
    0.88
     autorytatywna
    0.79
    TS
    0.78
    __":
    
    0.75
    ")){
    
    0.74
    }")
    
    0.72
     fieldNum
    0.70
    ets
    0.69
    tsin
    0.69
    Activations Density 2.102%

    No Known Activations