© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10544
    Prev
    Next
    INDEX
    Explanations

    elements of romance amidst conflict or danger

    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
     itſelf
    -0.97
     ſche
    -0.90
     iſt
    -0.86
     ſtate
    -0.84
    Datuak
    -0.83
     Jefus
    -0.83
    ContentAsync
    -0.82
     raiſ
    -0.81
     cauſe
    -0.81
     ſta
    -0.80
    POSITIVE LOGITS
    ollectionView
    0.49
     cuer
    0.47
     Ver
    0.45
     hoved
    0.45
     rom
    0.42
    Ver
    0.42
    VER
    0.40
     "
    0.40
    esri
    0.39
     dynamically
    0.39
    Activations Density 0.345%

    No Known Activations