© 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. 734
    Prev
    Next
    INDEX
    Explanations

    specific phrases or structures within technical or computer-related discussions

    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
    PYX
    -0.73
     without
    -0.65
    부터
    -0.63
     after
    -0.62
    Personendaten
    -0.61
     from
    -0.59
     with
    -0.56
    ỡng
    -0.56
    without
    -0.55
     since
    -0.53
    POSITIVE LOGITS
     dans
    1.17
     en
    1.02
     nella
    0.98
     katika
    0.97
     trong
    0.93
     в
    0.91
     في
    0.90
     nel
    0.90
     nell
    0.90
     în
    0.87
    Activations Density 0.077%

    No Known Activations