© 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. 16-GEMMASCOPE-RES-16K
    11. 1351
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connectors indicating relationships between ideas or components

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

    Follows conjunctions "and" or "but"

    np_acts-logits-general · gemini-2.0-flash

    conjunctions followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.96
     Efq
    -0.87
     ſame
    -0.86
     faſt
    -0.86
     purpoſe
    -0.85
     iſt
    -0.84
    neſs
    -0.84
     Monfieur
    -0.83
     greateſt
    -0.83
     ſmall
    -0.82
    POSITIVE LOGITS
     -
    0.53
     
    0.51
     ans
    0.50
     at
    0.48
    EdgeInsets
    0.48
     يلي
    0.48
     here
    0.46
    InjectAttribute
    0.46
     i
    0.45
     e
    0.45
    Activations Density 0.028%

    No Known Activations