© 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. 8-GEMMASCOPE-RES-16K
    11. 5015
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and measurements related to objects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spare
    -0.57
    ppy
    -0.57
     Italijanski
    -0.57
    atist
    -0.56
    atists
    -0.56
     utafitiHapana
    -0.55
     bezeichneter
    -0.55
    paksa
    -0.55
    berd
    -0.55
    ToolStrip
    -0.55
    POSITIVE LOGITS
     and
    0.83
     or
    0.75
    和
    0.61
    دانشنامهٔ
    0.58
    /
    0.56
     или
    0.55
    webElementXpaths
    0.55
     和
    0.55
     للاسماء
    0.54
    Népesség
    0.53
    Activations Density 1.137%

    No Known Activations