© 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. 1718
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain clinical or technical medical terminologies

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

    Text followed by the token "Q" or "4"

    np_acts-logits-general · gemini-2.0-flash

    Q: followed by questions

    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
     qu
    -0.74
     sa
    -0.72
     in
    -0.71
    الدراسه
    -0.71
     […]
    -0.71
     to
    -0.69
     m
    -0.69
     der
    -0.69
     br
    -0.69
     bu
    -0.68
    POSITIVE LOGITS
     pleaſure
    1.10
     myſelf
    1.07
     ſmall
    0.98
     leſs
    0.97
     Sarm
    0.97
     themſelves
    0.97
     itſelf
    0.96
     reaſon
    0.95
     purpoſe
    0.95
     ſame
    0.95
    Activations Density 0.010%

    No Known Activations