© 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. 19-GEMMASCOPE-RES-16K
    11. 5191
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and their dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.54
     equinox
    -0.52
     parades
    -0.52
    kań
    -0.48
    JNIEnv
    -0.47
    Décès
    -0.47
     jsPsych
    -0.47
     bloat
    -0.47
    ActionCreators
    -0.47
    Geografía
    -0.47
    POSITIVE LOGITS
     relationship
    2.81
     relationships
    2.48
     relations
    2.29
    relationship
    2.29
     Relationship
    2.26
     RELATIONSHIP
    2.19
     relation
    2.19
    Relationship
    2.12
     Relationships
    2.04
    relationships
    1.94
    Activations Density 0.738%

    No Known Activations