© 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. 11055
    Prev
    Next
    INDEX
    Explanations

    important concepts and principles related to communication, consistency, and education

    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
    fromnode
    -0.81
    
    -0.76
    <unused80>
    -0.76
    <unused41>
    -0.75
    <unused74>
    -0.75
    <unused23>
    -0.75
    <unused47>
    -0.75
    <unused79>
    -0.75
    <unused14>
    -0.75
    <unused28>
    -0.75
    POSITIVE LOGITS
     recipe
    0.58
     kunci
    0.53
     key
    0.50
     antidote
    0.43
     keys
    0.43
    Recipe
    0.41
     priceless
    0.41
    Key
    0.40
    key
    0.40
    🔑
    0.40
    Activations Density 0.363%

    No Known Activations