© 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 - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8391
    Prev
    Next
    INDEX
    Explanations

    measurements and units of centimeters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.64
    SPJ
    -0.57
    Золо
    -0.55
    setVerticalGroup
    -0.54
     Cass
    -0.53
    strtotime
    -0.53
    cass
    -0.53
    orance
    -0.51
    Câ
    -0.51
     uLocal
    -0.51
    POSITIVE LOGITS
    cm
    3.23
     cm
    3.11
     centimeters
    1.99
    CM
    1.92
     CM
    1.90
     centimeter
    1.86
    Cm
    1.76
     Cm
    1.75
     centimetres
    1.70
    ｃｍ
    1.65
    Activations Density 0.051%

    No Known Activations