© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 10120
    Prev
    Next
    INDEX
    Explanations

    elements related to statistical analysis and quantifiable data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eight
    -1.88
     six
    -1.86
     seven
    -1.86
     nine
    -1.86
     five
    -1.84
     four
    -1.76
     twelve
    -1.70
     fifteen
    -1.69
     fourteen
    -1.68
     thirteen
    -1.68
    POSITIVE LOGITS
    SequentialGroup
    0.62
    存于互联网档案馆
    0.40
    )=>{
    0.40
    \}=\
    0.39
     prochaines
    0.39
    !="
    0.38
    *
    0.38
    ={(
    0.36
    !='
    0.36
    GeoNames
    0.36
    Activations Density 1.502%

    No Known Activations