© 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. 2-GEMMASCOPE-RES-16K
    11. 15643
    Prev
    Next
    INDEX
    Explanations

    references to files and media types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    صة
    -0.53
    MessageDigest
    -0.53
     Pristupljeno
    -0.52
     Gallagher
    -0.51
    TopLeft
    -0.49
     Rewards
    -0.49
    preventDefault
    -0.48
    tiers
    -0.48
     rewards
    -0.47
    link
    -0.47
    POSITIVE LOGITS
     films
    1.61
     videos
    1.40
     Films
    1.29
     papers
    1.28
    Films
    1.28
     movies
    1.22
     poems
    1.16
     novels
    1.15
     Videos
    1.14
     Papers
    1.13
    Activations Density 0.203%

    No Known Activations