© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 14172
    Prev
    Next
    INDEX
    Explanations

    terms related to reconstruction and rebuilding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.74
    catraz
    -0.51
    ThroughAttribute
    -0.47
    formik
    -0.47
    ensory
    -0.46
    emitter
    -0.46
    GetMapping
    -0.46
    apimachinery
    -0.45
    RTHOOK
    -0.45
    Hrsg
    -0.45
    POSITIVE LOGITS
     rebuild
    2.24
     reviving
    2.22
     revived
    2.18
     revive
    2.18
     revival
    2.17
     rebuilding
    2.17
     rebuilt
    2.03
     revital
    1.98
     restart
    1.97
     restarting
    1.96
    Activations Density 0.104%

    No Known Activations