Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11255
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and numerical relationships related to experimental measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    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
    -0.66
     cherchés
    -0.52
     незавершена
    -0.47
     betweenstory
    -0.46
     EconPapers
    -0.41
    setFrame
    -0.41
     @"/
    -0.40
     estekak
    -0.40
    enderror
    -0.40
     NSCoder
    -0.40
    POSITIVE LOGITS
     linear
    1.19
    linear
    1.01
     linearity
    0.97
     exponential
    0.96
     curve
    0.96
     liné
    0.96
     linearly
    0.94
     proportionality
    0.91
     LINEAR
    0.87
     Linear
    0.86
    Activations Density 2.211%

    No Known Activations