© 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-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 634
    Prev
    Next
    INDEX
    Explanations

    function definitions and return statements within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.87
    RegressionTest
    -0.76
    offsetof
    -0.75
     يتيمه
    -0.73
     سكانية
    -0.72
    Зноскі
    -0.70
     autorytatywna
    -0.69
     CreateTagHelper
    -0.68
    PyExc
    -0.67
     المعيارى
    -0.67
    POSITIVE LOGITS
     mixed
    0.48
     The
    0.47
     -
    0.46
    </i>
    0.45
    ↵
    0.44
    |
    0.41
    </b>
    0.41
    void
    0.40
     Returns
    0.40
    mixed
    0.39
    Activations Density 0.132%

    No Known Activations