© 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. 0-GEMMASCOPE-RES-16K
    11. 3166
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and libraries, particularly for Java and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lysm
    -0.51
     szolg
    -0.46
     --
    -0.46
     payout
    -0.44
     geschlagen
    -0.44
     zprá
    -0.43
    ARGB
    -0.43
    -->
    -0.43
    fillStyle
    -0.43
     -->
    -0.42
    POSITIVE LOGITS
    +#+
    0.85
     Conferences
    0.80
    IUrlHelper
    0.77
    conference
    0.76
    Conference
    0.75
     Conference
    0.75
    ginal
    0.74
    fjspx
    0.74
    AutoresizingMask
    0.72
     conferences
    0.71
    Activations Density 2.563%

    No Known Activations