© 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. 18-GEMMASCOPE-RES-16K
    11. 6914
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and instructions within technical contexts

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

    that introduce a reason/condition

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and discourse markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -1.06
     myſelf
    -1.00
     Monfieur
    -0.95
     ſever
    -0.91
     faſt
    -0.91
     ſeveral
    -0.88
     ſind
    -0.86
    seamnă
    -0.86
     houſe
    -0.85
     purpoſe
    -0.84
    POSITIVE LOGITS
     entire
    0.78
     latter
    0.75
     main
    0.72
     final
    0.64
     situation
    0.62
     ENTIRE
    0.61
     same
    0.60
     story
    0.56
    entire
    0.56
     whole
    0.55
    Activations Density 0.118%

    No Known Activations