© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15151
    Prev
    Next
    INDEX
    Explanations

    text relating to family and relationships, particularly in contexts surrounding death and remembrance

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

    Following a name or date

    np_acts-logits-general · gemini-2.0-flash

    funeral and survivors

    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
    ValueStyle
    -0.66
    principalColumn
    -0.61
    AnchorStyles
    -0.58
    我才
    -0.55
    Почему
    -0.54
     Why
    -0.51
    anmoins
    -0.51
     this
    -0.50
    mes
    -0.50
     discou
    -0.50
    POSITIVE LOGITS
     Survivors
    0.97
    Survivors
    0.94
     survivors
    0.94
     Survi
    0.86
    Surviving
    0.85
    Funeral
    0.78
     surviving
    0.76
     Funeral
    0.72
    survi
    0.72
     funeral
    0.70
    Activations Density 0.019%

    No Known Activations