© 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. 24-GEMMASCOPE-RES-16K
    6. 5154
    Prev
    Next
    INDEX
    Explanations

    phrases related to a person's life events, milestones, and familial relationships

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

    Follows "is" or "was," indicating a state or condition

    np_acts-logits-general · gemini-2.0-flash

    past states and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.53
    :✨
    -0.52
    rables
    -0.51
    chtet
    -0.49
     drinkers
    -0.49
    ませ
    -0.49
     ögon
    -0.48
    eaways
    -0.47
    INP
    -0.47
     gynnwys
    -0.46
    POSITIVE LOGITS
     preceded
    1.00
     survived
    1.00
     proceeded
    0.91
     predeceased
    0.89
    Survi
    0.72
     Survi
    0.69
     prede
    0.69
     précé
    0.69
     survi
    0.68
     precede
    0.67
    Activations Density 0.071%

    No Known Activations