© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 40931
    Prev
    Next
    INDEX
    Explanations

    phrases that begin with the word "Have."

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

    Have a / you / been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.57
     Cik
    -0.56
     insign
    -0.52
    optarg
    -0.51
     MatDialog
    -0.49
    Mq
    -0.49
    skirts
    -0.48
    fjspx
    -0.48
    ₁(
    -0.48
    fileInfo
    -0.48
    POSITIVE LOGITS
    Have
    0.89
     Have
    0.84
    have
    0.77
     have
    0.70
     Hassel
    0.68
     HAVE
    0.62
    HAVE
    0.60
     had
    0.58
     haben
    0.56
     Hãy
    0.55
    Activations Density 0.009%

    No Known Activations