© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11325
    Prev
    Next
    INDEX
    Explanations

    software and applications related to downloading and file management

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

    Free downloads, proxies, and VPNs

    np_acts-logits-general · gemini-2.0-flash

    unlimited proxy or VPN

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etsy
    -0.52
    fromnode
    -0.51
    igrette
    -0.47
    ftagPool
    -0.46
     Lehr
    -0.46
    glie
    -0.45
    routeProvider
    -0.44
    evt
    -0.44
    beur
    -0.43
    TacToe
    -0.43
    POSITIVE LOGITS
     dumps
    0.69
     cheats
    0.67
     proxies
    0.64
     cheat
    0.62
     fake
    0.62
     Free
    0.61
     legalization
    0.61
     ilegal
    0.61
     Proxy
    0.61
     fakes
    0.60
    Activations Density 0.270%

    No Known Activations