© 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. 11-GEMMASCOPE-RES-16K
    11. 1219
    Prev
    Next
    INDEX
    Explanations

    responses and actions related to communication or addressing issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NgModule
    -0.78
     للمعارف
    -0.64
     насељу
    -0.64
     Knowledge
    -0.60
     knowledge
    -0.60
    الدراسه
    -0.57
    Knowledge
    -0.57
    knowledge
    -0.56
    useNewUrlParser
    -0.55
    BeginContext
    -0.55
    POSITIVE LOGITS
     respond
    1.55
     responds
    1.54
     responses
    1.53
     response
    1.48
     responded
    1.47
     Respond
    1.44
     responding
    1.42
     RESPONSE
    1.38
     RESPOND
    1.34
     Responding
    1.32
    Activations Density 0.186%

    No Known Activations