© 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. 15-GEMMASCOPE-RES-16K
    11. 3999
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and inquiries about specific outcomes or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ślę
    -0.51
     surprisingly
    -0.50
     usually
    -0.49
     KeyError
    -0.48
     jLabel
    -0.46
    extAlignment
    -0.45
    =-=-=-=-
    -0.45
    arsky
    -0.45
    usually
    -0.45
     geme
    -0.44
    POSITIVE LOGITS
    contentLoaded
    0.87
    windowFixed
    0.79
    fjspx
    0.77
     protoimpl
    0.75
    IVEREF
    0.70
     typelib
    0.69
    MessageTagHelper
    0.68
     kaarangay
    0.67
    MigrationBuilder
    0.67
    :✨
    0.67
    Activations Density 0.229%

    No Known Activations