© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4701
    Prev
    Next
    INDEX
    Explanations

    phrases related to social behaviors and interpersonal dynamics

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

    Punctuation followed by a function word

    np_acts-logits-general · gemini-2.0-flash

    describing routines and habits

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     NSCoder
    -0.42
     незавершена
    -0.42
     Frieden
    -0.41
     vetorial
    -0.40
    BufferException
    -0.40
    EndInit
    -0.39
     éché
    -0.39
     ***!
    -0.38
     kebijakan
    -0.38
     partij
    -0.38
    POSITIVE LOGITS
     habits
    0.54
    habit
    0.52
     lifestyle
    0.51
     hábito
    0.50
     habit
    0.47
     Habits
    0.46
    Habit
    0.45
     utafitiHapana
    0.45
    lifestyle
    0.45
    Lifestyle
    0.45
    Activations Density 0.454%

    No Known Activations