© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11415
    Prev
    Next
    INDEX
    Explanations

    references to materials and packaging methods

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

    packaging or wrapping

    np_acts-logits-general · gemini-2.0-flash

    packaging and wrapping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.66
    icago
    -0.61
     initComponents
    -0.61
    κτή
    -0.60
     sumpay
    -0.56
    ExtendWith
    -0.56
     <>",
    -0.53
     Pinto
    -0.53
     فريبيس
    -0.53
     interpol
    -0.53
    POSITIVE LOGITS
     packaging
    1.82
     wrapping
    1.59
     Packaging
    1.51
     wrap
    1.41
    packaging
    1.39
    Packaging
    1.35
     packing
    1.35
     wrapped
    1.33
     Wrapping
    1.33
     wrapper
    1.31
    Activations Density 0.206%

    No Known Activations