© 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. 8155
    Prev
    Next
    INDEX
    Explanations

    concepts related to reversing and changing states or orders

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

    an opposite or reverse relationship

    np_acts-logits-general · gemini-2.0-flash

    reverse, opposite, contrary

    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
    atisfactory
    -0.46
    طلحات
    -0.43
     tolerancia
    -0.42
     tolerated
    -0.42
     anges
    -0.42
    まと
    -0.42
     recommandée
    -0.40
     hạn
    -0.40
    JspWriter
    -0.40
    ktan
    -0.39
    POSITIVE LOGITS
     reverse
    3.19
     reversed
    2.91
     Reverse
    2.79
    reverse
    2.71
    Reverse
    2.65
     reverses
    2.64
     reversal
    2.59
     reversing
    2.56
     revers
    2.36
    reversed
    2.36
    Activations Density 0.762%

    No Known Activations