© 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. 4986
    Prev
    Next
    INDEX
    Explanations

    references to the action of putting something in a specific location or context

    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
     Hick
    -0.65
    ("}");
    -0.62
    phazard
    -0.57
     uintptr
    -0.57
    sertation
    -0.57
     Dutton
    -0.56
    IsPostBack
    -0.56
    Đây
    -0.56
    gaben
    -0.55
    SPONSORED
    -0.54
    POSITIVE LOGITS
    Place
    2.34
    place
    2.22
     Place
    2.19
     placing
    2.13
    PLACE
    2.06
     Placing
    2.02
     PLACE
    1.98
     placed
    1.87
    placing
    1.84
    Placed
    1.77
    Activations Density 0.118%

    No Known Activations