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

    Neuronpedia

    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. 2-GEMMASCOPE-RES-16K
    11. 7572
    Prev
    Next
    INDEX
    Explanations

    discussions and interactions related to dialogue or conversations

    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
     CreateTagHelper
    -0.74
    AsUp
    -0.58
    Carriera
    -0.57
    ="<?=
    -0.57
     BorderRadius
    -0.54
    agissait
    -0.54
     named
    -0.54
    asi
    -0.54
    as
    -0.53
    espan
    -0.53
    POSITIVE LOGITS
     dialogue
    1.24
    dialogue
    1.14
     Dialogue
    1.03
     dialog
    0.94
    Dialogue
    0.92
     DIALOG
    0.92
     diálogo
    0.90
     dialogues
    0.87
     Oxygen
    0.74
    Oxygen
    0.73
    Activations Density 0.038%

    No Known Activations