© 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. 4-GEMMASCOPE-RES-16K
    11. 15779
    Prev
    Next
    INDEX
    Explanations

    references to general information or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^(@)
    -0.87
     Adkins
    -0.87
     myſelf
    -0.82
    Попис
    -0.81
     Huguen
    -0.80
    InputTagHelper
    -0.79
    wußt
    -0.78
    resave
    -0.77
    ougars
    -0.77
     Nantucket
    -0.76
    POSITIVE LOGITS
     general
    2.70
     General
    2.62
    General
    2.57
    general
    2.52
     GENERAL
    2.39
    GENERAL
    2.35
     generale
    2.01
    eneral
    1.97
     général
    1.88
     generales
    1.82
    Activations Density 0.083%

    No Known Activations