© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15259
    Prev
    Next
    INDEX
    Explanations

    references to mathematical expressions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.80
    Personendaten
    -0.78
     disambiguazione
    -0.75
    "?>
    -0.69
    
    -0.67
    <unused74>
    -0.66
     deleteById
    -0.66
    <unused43>
    -0.66
     Dieſe
    -0.66
    <unused8>
    -0.66
    POSITIVE LOGITS
     koje
    0.34
    t
    0.34
     while
    0.33
    s
    0.32
     funziona
    0.32
     Heilige
    0.32
     comunista
    0.31
     Furcht
    0.31
     koja
    0.31
     distinto
    0.31
    Activations Density 0.039%

    No Known Activations