© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13435
    Prev
    Next
    INDEX
    Explanations

    patterns related to coding or programming syntax

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

    Numbers after "x" or other numbers

    np_acts-logits-general · gemini-2.0-flash

    hex numbers followed by 8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seventeen
    -0.59
    XVII
    -0.58
    JULY
    -0.57
    Datuak
    -0.56
    BufferException
    -0.56
     cref
    -0.54
    VII
    -0.54
    十七
    -0.54
    ⑦
    -0.53
     violation
    -0.53
    POSITIVE LOGITS
    IndentedString
    0.67
     tartalomajánló
    0.58
    windowFixed
    0.58
    8
    0.54
    RegressionTest
    0.53
    ⑧
    0.51
    oa̍t
    0.49
    GEBURTSDATUM
    0.49
     ThemeData
    0.49
    horizontalLayout
    0.49
    Activations Density 0.235%

    No Known Activations