© 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. 22-GEMMASCOPE-RES-16K
    11. 8518
    Prev
    Next
    INDEX
    Explanations

    file-related references and error messages in code

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

    "File" followed by a file path

    np_acts-logits-general · gemini-2.0-flash

    file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WillAppear
    -0.74
    oa̍t
    -0.73
    InjectAttribute
    -0.69
    WithIOException
    -0.69
    Personendaten
    -0.68
     PyLong
    -0.67
    WindowConstants
    -0.66
    tanleria
    -0.65
    QMetaType
    -0.65
    SharedCtor
    -0.65
    POSITIVE LOGITS
    filepath
    0.48
     filepath
    0.47
    مراجع
    0.44
     bav
    0.42
    usercontent
    0.41
    IZING
    0.40
    inaldo
    0.40
    abestanden
    0.39
     счёт
    0.39
    unku
    0.39
    Activations Density 0.063%

    No Known Activations