© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15653
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and qualifiers in scientific contexts

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

    "Unless" followed by a qualifying statement

    np_acts-logits-general · gemini-2.0-flash

    unless specified otherwise

    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
     Wor
    -0.47
     once
    -0.45
     Bef
    -0.44
    bo
    -0.44
    once
    -0.44
     Once
    -0.43
    ={()
    -0.43
    Once
    -0.42
    hasMoreElements
    -0.41
     recentes
    -0.41
    POSITIVE LOGITS
     specified
    1.19
     indicated
    1.19
    specified
    1.06
    indicated
    0.97
     Specified
    0.97
     stated
    0.91
     otherwise
    0.89
     explicitly
    0.84
    otherwise
    0.84
    noted
    0.82
    Activations Density 0.341%

    No Known Activations