© 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. 33-GEMMASCOPE-RES-16K
    6. 574
    Prev
    Next
    INDEX
    Explanations

    specific layout properties and settings in code snippets

    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
    scrollLeft
    -0.56
     getWidth
    -0.53
     husband
    -0.50
    wider
    -0.50
     width
    -0.50
    translateX
    -0.50
    husband
    -0.49
    screenWidth
    -0.49
    width
    -0.47
    CrossRef
    -0.47
    POSITIVE LOGITS
     getHeight
    0.83
     height
    0.81
    Height
    0.75
     Height
    0.75
    height
    0.71
     HEIGHT
    0.70
     heights
    0.66
    HEIGHT
    0.66
    offsetHeight
    0.63
     hauteur
    0.62
    Activations Density 0.320%

    No Known Activations