© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31387
    Prev
    Next
    INDEX
    Explanations

    language related to caution and forward-looking statements

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

    any or that can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tasar
    -0.45
    nativeElement
    -0.45
     EXC
    -0.44
    CDATA
    -0.43
     modal
    -0.43
     vass
    -0.43
    ِن
    -0.42
     Sut
    -0.42
    dcmtk
    -0.42
     assert
    -0.42
    POSITIVE LOGITS
     виправивши
    0.80
     cherchés
    0.76
    RenderAtEndOf
    0.73
     مشين
    0.63
    RUnlock
    0.63
    تقاوى
    0.63
    WriteTagHelper
    0.62
     bParam
    0.61
     ProtoMessage
    0.60
    writeFieldEnd
    0.59
    Activations Density 0.036%

    No Known Activations