© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 6032
    Prev
    Next
    INDEX
    Explanations

    elements related to programming concepts and control structures

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

    Code blocks and conditional statements

    np_acts-logits-general · gemini-2.0-flash

    existing conditions or else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.61
    новништво
    -0.56
     ""],
    -0.43
    tagPool
    -0.41
     Wiktionnaire
    -0.38
    Legende
    -0.38
    ंदीखरीदारी
    -0.38
     Tenggara
    -0.37
     kaarangay
    -0.37
    )$/,
    -0.37
    POSITIVE LOGITS
     otherwise
    3.59
     Otherwise
    3.22
    Otherwise
    3.13
    otherwise
    3.13
     OTHERWISE
    2.59
     altrimenti
    2.55
     sonst
    2.45
     else
    2.30
    否则
    2.28
     иначе
    2.23
    Activations Density 0.769%

    No Known Activations