© 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. 661
    Prev
    Next
    INDEX
    Explanations

    conversational elements expressing confusion, inquiry, and attempts to understand complex situations

    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
     ')
    -0.53
    mişti
    -0.51
    diğinde
    -0.49
     
    -0.48
     murs
    -0.47
    ')
    -0.46
    melidir
    -0.46
     on
    -0.44
    "}"
    -0.44
    =");
    -0.43
    POSITIVE LOGITS
    MigrationBuilder
    0.97
    principalColumn
    0.96
    ContentAsync
    0.93
    __':
    0.82
    __':
    0.79
    expandindo
    0.77
    verwijspagina
    0.77
     CreateTagHelper
    0.75
    Diwedd
    0.73
    enumi
    0.71
    Activations Density 1.395%

    No Known Activations