© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 1647
    Prev
    Next
    INDEX
    Explanations

    technical measurements and specifications related to experimental setups

    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
     defaultstate
    -0.78
     >=",
    -0.70
     useAuth
    -0.63
    insegna
    -0.58
    Personendaten
    -0.57
     Réponses
    -0.55
    ViewHolder
    -0.52
     logits
    -0.51
     surla
    -0.51
    EXISTS
    -0.50
    POSITIVE LOGITS
     discretization
    1.04
     step
    0.96
     resolution
    0.91
     finer
    0.91
     grid
    0.87
    step
    0.85
     Шаг
    0.84
     mesh
    0.83
     fine
    0.82
    resolution
    0.81
    Activations Density 1.417%

    No Known Activations