© 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. 22-GEMMASCOPE-RES-16K
    11. 10812
    Prev
    Next
    INDEX
    Explanations

    discussions about conditionality and alternative scenarios

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

    "...but" or "...instead" appearing in text

    np_acts-logits-general · gemini-2.0-flash

    but instead/rather

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     not
    -2.23
     não
    -2.09
     nicht
    -1.95
     tidak
    -1.90
     niet
    -1.88
     ikke
    -1.87
     doesn
    -1.79
    not
    -1.73
     neither
    -1.72
     didn
    -1.71
    POSITIVE LOGITS
    rungsseite
    0.77
     مرئيه
    0.74
     nakalista
    0.74
     препратки
    0.73
     متعلقه
    0.70
    Autoritní
    0.69
     autorytatywna
    0.66
     EconPapers
    0.62
    >",
    0.60
     rospy
    0.58
    Activations Density 1.123%

    No Known Activations