© 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. 508
    Prev
    Next
    INDEX
    Explanations

    sections related to scientific studies and findings

    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
     Ceux
    -0.64
     anything
    -0.61
    Anything
    -0.60
    每一个
    -0.60
     every
    -0.59
    OGND
    -0.59
     everything
    -0.58
    Diwedd
    -0.58
     оригіналу
    -0.58
     meeste
    -0.57
    POSITIVE LOGITS
     similarly
    1.03
     unrelated
    0.94
     than
    0.89
     equally
    0.88
     nearby
    0.85
     besides
    0.84
     igualmente
    0.84
     similar
    0.83
     serupa
    0.81
    nearby
    0.78
    Activations Density 0.459%

    No Known Activations