© 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. 8260
    Prev
    Next
    INDEX
    Explanations

    phrases that express passion or attachment

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

    "A" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    a habit or tendency

    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
     fiind
    -0.60
     évent
    -0.56
     eventuali
    -0.49
     esfuerzo
    -0.48
    chenkt
    -0.48
     للمعارف
    -0.48
     esforço
    -0.46
     ayant
    -0.46
     évit
    -0.44
     betweenstory
    -0.44
    POSITIVE LOGITS
     tendency
    1.01
     knack
    0.90
     penchant
    0.90
     vested
    0.88
     problem
    0.81
    AndEndTag
    0.76
     fondness
    0.74
     habit
    0.73
     aversion
    0.73
     choice
    0.71
    Activations Density 0.229%

    No Known Activations