© 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. 5-GEMMASCOPE-RES-16K
    11. 2933
    Prev
    Next
    INDEX
    Explanations

    verbs and actions that involve significant impact or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    actions and contributions related to significant achievements or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.60
    Xna
    -0.43
     piti
    -0.42
     trent
    -0.40
    PRINTF
    -0.40
    OnItem
    -0.40
     due
    -0.40
    PreferredItem
    -0.39
     cser
    -0.39
     adenocarcinoma
    -0.38
    POSITIVE LOGITS
    NUMX
    0.87
    
    0.85
    تقاوى
    0.83
    Diwedd
    0.74
    )$/,
    0.72
     BoxFit
    0.72
    haustible
    0.71
     שוליים
    0.71
    homonymie
    0.69
     Pave
    0.68
    Activations Density 0.389%

    No Known Activations