© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 7430
    Prev
    Next
    INDEX
    Explanations

    references to habits and routines, especially in relation to personal growth and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.63
    TagMode
    -0.47
     חיצוניים
    -0.40
    ännande
    -0.39
     Italijanski
    -0.39
    esez
    -0.39
    ']>;
    -0.39
    󠁴
    -0.38
    SpringRunner
    -0.38
    ništvo
    -0.38
    POSITIVE LOGITS
     habit
    2.66
     habits
    2.45
     Habit
    2.25
     hábito
    2.23
     Habits
    2.14
    Habit
    2.11
    habit
    2.06
    习惯
    1.98
    習慣
    1.95
     kebiasaan
    1.88
    Activations Density 0.398%

    No Known Activations