© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3522
    Prev
    Next
    INDEX
    Explanations

    code termination characters and syntax indicators

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

    Code, symbols, and foreign language fragments

    np_acts-logits-general · gemini-2.0-flash

    code punctuation

    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
     heil
    -0.56
    丘
    -0.54
     mer
    -0.52
    vine
    -0.50
    няются
    -0.50
     ريا
    -0.49
    feu
    -0.49
    ()==
    -0.48
    чет
    -0.47
    hava
    -0.45
    POSITIVE LOGITS
    StoryboardSegue
    0.96
    IndentedString
    0.95
     صوتيه
    0.91
    LookAnd
    0.88
     transfieras
    0.86
    :✨
    0.85
    GEBURTSDATUM
    0.85
     فريبيس
    0.80
     Normdatei
    0.77
     typelib
    0.76
    Activations Density 0.151%

    No Known Activations