© 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. 576
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to norms and Banach spaces

    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
     ब्रेकडाउन
    -0.44
     للمعارف
    -0.44
    RenderAtEndOf
    -0.44
     ligiloj
    -0.42
     [{
    -0.38
    {(-
    -0.36
     Nectar
    -0.36
     BoxDecoration
    -0.36
     @
    -0.35
    GEBURTS
    -0.35
    POSITIVE LOGITS
     $\|
    1.00
    \|
    0.85
    }\|
    0.84
     norms
    0.83
     norm
    0.78
    Nor
    0.75
     normes
    0.74
     Nor
    0.74
     norma
    0.74
     NOR
    0.73
    Activations Density 2.150%

    No Known Activations