© 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. 18-GEMMASCOPE-RES-16K
    11. 4436
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy and condolences in the context of loss or mourning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interest
    -0.61
    Personendaten
    -0.59
    Географи
    -0.57
    sprzedam
    -0.56
     interested
    -0.56
    ülü
    -0.55
     علاقه
    -0.55
    shadowOpacity
    -0.55
    IOUS
    -0.54
    Curious
    -0.54
    POSITIVE LOGITS
    MigrationBuilder
    0.69
     ComVisible
    0.60
     prayers
    0.56
    Datuak
    0.56
    VersionUID
    0.55
    TestingModule
    0.55
    enumii
    0.54
     prays
    0.53
    wapV
    0.51
     Prayers
    0.49
    Activations Density 0.028%

    No Known Activations