© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8451
    Prev
    Next
    INDEX
    Explanations

    function definitions and variable assignments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.57
    WithIOException
    -0.49
    IndentedString
    -0.48
    hasMoreElements
    -0.47
    <bos>
    -0.47
     Jane
    -0.46
    TypedDataSet
    -0.45
     letter
    -0.44
     extra
    -0.44
    QMetaType
    -0.43
    POSITIVE LOGITS
    حياتها
    0.80
    __(/*!
    0.79
     ddelweddau
    0.69
     المعيارى
    0.66
     الحره
    0.66
     vectorielles
    0.65
     Partagez
    0.65
    ۜ
    0.64
     Shaksp
    0.63
     feroit
    0.62
    Activations Density 0.123%

    No Known Activations