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

    Neuronpedia

    Jacobian LensNEW
    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. 22-GEMMASCOPE-RES-16K
    11. 4630
    Prev
    Next
    INDEX
    Explanations

    references to academic proceedings and conference papers

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

    "of" followed by "the"

    np_acts-logits-general · gemini-2.0-flash

    academic conference proceedings

    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
    ModelSerializer
    -0.54
     onBind
    -0.51
    akterysty
    -0.50
    alib
    -0.47
     endom
    -0.46
     joaat
    -0.45
    ($__
    -0.44
    ConverterFactory
    -0.44
    ModelForm
    -0.44
    imetsu
    -0.43
    POSITIVE LOGITS
     ACM
    0.88
    ACM
    0.77
    SIG
    0.70
     SIG
    0.68
     mergeFrom
    0.65
    
    0.63
    RenderAtEndOf
    0.62
     Computer
    0.61
     يتيمه
    0.61
    acm
    0.60
    Activations Density 0.369%

    No Known Activations