© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 13037
    Prev
    Next
    INDEX
    Explanations

    data structures related to dictionaries or associative arrays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Хьажоргаш
    -0.46
    odils
    -0.44
     <=",
    -0.43
    epik
    -0.42
    TemporalType
    -0.40
    
    -0.40
     detectable
    -0.40
    robots
    -0.39
    SBATCH
    -0.38
     viewType
    -0.38
    POSITIVE LOGITS
    NSDictionary
    0.85
     HashMap
    0.81
    HashMap
    0.81
    Hashtable
    0.77
     Hashtable
    0.72
    dict
    0.71
     LinkedHashMap
    0.70
    DBObject
    0.67
    LinkedHashMap
    0.66
    Dict
    0.66
    Activations Density 0.485%

    No Known Activations