© 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. 5-GEMMASCOPE-RES-16K
    11. 7210
    Prev
    Next
    INDEX
    Explanations

    the concept of "missing" or absence related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.73
    WriteTagHelper
    -0.69
    anwal
    -0.68
    yttä
    -0.68
     Edelman
    -0.67
    stackoverflow
    -0.67
    ResumeLayout
    -0.67
     שוליים
    -0.66
     arrayed
    -0.66
    cektir
    -0.66
    POSITIVE LOGITS
     miss
    2.12
     MISS
    2.07
     misses
    1.96
    miss
    1.90
    Miss
    1.90
     Missing
    1.90
     missing
    1.83
    MISS
    1.82
    Missing
    1.77
     missed
    1.77
    Activations Density 0.070%

    No Known Activations