© 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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 15361
    Prev
    Next
    INDEX
    Explanations

    numerical references to technical specifications and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.86
     Broadway
    -0.58
    UserScript
    -0.57
    Portale
    -0.54
    phrine
    -0.53
    året
    -0.53
     theatres
    -0.51
     curtains
    -0.50
    QMetaType
    -0.50
     متعلقه
    -0.49
    POSITIVE LOGITS
     storage
    1.13
     Storage
    1.09
    Storage
    0.99
     STORAGE
    0.98
    storage
    0.93
     disk
    0.84
    STORAGE
    0.84
     HDD
    0.83
     drives
    0.77
     Disk
    0.77
    Activations Density 0.301%

    No Known Activations