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. 0-GEMMASCOPE-RES-16K
    6. 7956
    Prev
    Next
    INDEX
    Explanations

    mentions of the chemical compound AZ and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.56
     acess
    -0.47
     properties
    -0.46
     poignée
    -0.46
     Holiday
    -0.45
     reaches
    -0.45
     táctil
    -0.44
     access
    -0.44
     places
    -0.43
     bonté
    -0.43
    POSITIVE LOGITS
    Exciting
    0.71
     Exciting
    0.68
    Personendaten
    0.65
    Excited
    0.60
    az
    0.60
     excitedly
    0.57
     Excited
    0.55
     Normdatei
    0.50
     az
    0.50
     excite
    0.50
    Activations Density 0.163%

    No Known Activations