© 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-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1542
    Prev
    Next
    INDEX
    Explanations

    parameters and annotations in function definitions or documentation comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/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.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
    reportWebVitals
    -0.58
     المعيارى
    -0.57
     Савезне
    -0.56
     betweenstory
    -0.54
    transQ
    -0.54
    BorderFactory
    -0.52
    RegressionTest
    -0.52
    MENAFN
    -0.51
    protoimpl
    -0.51
     OMITBAD
    -0.50
    POSITIVE LOGITS
    param
    1.00
     param
    0.57
     Param
    0.54
    Param
    0.51
     the
    0.49
     AttributeSet
    0.46
    ArgsConstructor
    0.43
    hdashline
    0.43
    joba
    0.41
    import
    0.41
    Activations Density 0.045%

    No Known Activations