Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10904
    Prev
    Next
    INDEX
    Explanations

    sentences discussing intentions behind tributes and memorials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Funeral or memorial-related contexts

    np_acts-logits-general · gemini-2.0-flash

    funeral and mourning tributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.60
     bored
    -0.52
     priming
    -0.50
     lenker
    -0.49
    fige
    -0.49
     Midas
    -0.49
    tocin
    -0.48
    hetamine
    -0.48
    apeno
    -0.47
     bootstra
    -0.47
    POSITIVE LOGITS
     mourners
    1.82
     mourning
    1.75
     grieving
    1.70
     funeral
    1.67
     memorial
    1.65
     condolences
    1.63
     tributes
    1.62
     condolence
    1.61
     mourn
    1.59
     bereaved
    1.54
    Activations Density 0.286%

    No Known Activations