© 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. 11063
    Prev
    Next
    INDEX
    Explanations

    references to methods or systems of communication and interaction

    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
    IndentedString
    -0.70
     transfieras
    -0.56
     الرياضيه
    -0.54
     оригіналу
    -0.53
    hlander
    -0.52
    évaluateur
    -0.51
     nakalista
    -0.51
     ujednoznacz
    -0.50
    getYear
    -0.50
    rungsseite
    -0.48
    POSITIVE LOGITS
     through
    1.19
     Through
    1.10
    Through
    1.09
    through
    1.08
     whereby
    0.98
     THROUGH
    0.94
     através
    0.91
     mediante
    0.90
     under
    0.88
     durch
    0.87
    Activations Density 0.262%

    No Known Activations