© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9211
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and constructs

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

    Code related to indentation or spaces

    np_acts-logits-general · gemini-2.0-flash

    string concatenation with indentation

    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
    EndInit
    -0.61
    发表于
    -0.57
     unbe
    -0.51
    省市镇
    -0.44
    cript
    -0.44
     exist
    -0.43
    čas
    -0.42
    ScopeManager
    -0.42
    CloseOperation
    -0.41
     basket
    -0.41
    POSITIVE LOGITS
    IndentedString
    0.77
    GEBURTSDATUM
    0.75
     indent
    0.70
     indentation
    0.69
     ویکی‌پدی
    0.66
    Indented
    0.66
    ########.
    0.64
     kaarangay
    0.63
    spaces
    0.63
    +#+#
    0.63
    Activations Density 0.428%

    No Known Activations