© 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. 3-GEMMASCOPE-RES-16K
    11. 5401
    Prev
    Next
    INDEX
    Explanations

    references to DVD and video formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useCallback
    -0.75
    putBoolean
    -0.60
    ">//
    -0.60
     Sen
    -0.60
     Mech
    -0.59
     Jorg
    -0.57
    //
    -0.56
     MonoBehaviour
    -0.56
     sen
    -0.55
    EXPERIMENTAL
    -0.55
    POSITIVE LOGITS
     DVD
    1.53
    DVD
    1.52
     DVDs
    1.40
     dvd
    1.35
     carpet
    1.20
     Carpet
    1.08
    tagHelperRunner
    1.08
    Carpet
    1.07
    carpet
    1.06
     itſelf
    1.02
    Activations Density 0.025%

    No Known Activations