© 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. 10954
    Prev
    Next
    INDEX
    Explanations

    questions and queries in a formal context

    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
     AssemblyCulture
    -0.94
     houſe
    -0.92
    IBarButtonItem
    -0.91
     Мексичка
    -0.90
     myſelf
    -0.89
     Houſe
    -0.88
     Majefty
    -0.86
     ―――――
    -0.85
    ^(@)
    -0.83
    ſelves
    -0.81
    POSITIVE LOGITS
     it
    1.03
     anyone
    0.97
     this
    0.91
     anybody
    0.86
     he
    0.81
    nt
    0.81
    Anybody
    0.72
    Anyone
    0.67
     Anybody
    0.65
    anyone
    0.64
    Activations Density 0.129%

    No Known Activations