Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 329
    Prev
    Next
    INDEX
    Explanations

    phrases that encourage self-improvement and personal motivation

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

    Habits, practices, or routines

    np_acts-logits-general · gemini-2.0-flash

    daily or weekly practices

    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
    GEBURTSDATUM
    -0.76
    InjectAttribute
    -0.76
    ")->
    -0.68
    writeFieldEnd
    -0.66
     الحره
    -0.65
    WithIOException
    -0.63
     Infórmanos
    -0.63
    __*/
    -0.62
     للمعارف
    -0.61
    DoubleQuotes
    -0.60
    POSITIVE LOGITS
     habit
    0.91
     weekly
    0.89
     habits
    0.84
     daily
    0.83
    Habit
    0.75
     WEEKLY
    0.74
     regel
    0.73
    weekly
    0.73
    習慣
    0.72
    habit
    0.71
    Activations Density 0.332%

    No Known Activations