© 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. 16-GEMMASCOPE-RES-16K
    6. 14473
    Prev
    Next
    INDEX
    Explanations

    elements related to vigilance and danger, particularly in the context of crisis situations

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

    following "their" or "begin"

    np_acts-logits-general · gemini-2.0-flash

    their

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myself
    -0.93
     my
    -0.83
    myself
    -0.70
    felf
    -0.65
     meines
    -0.64
    mylist
    -0.63
    PickerController
    -0.63
     meus
    -0.61
     meiner
    -0.61
     själv
    -0.61
    POSITIVE LOGITS
     themselves
    2.07
    Their
    1.73
     their
    1.71
    themselves
    1.69
     Their
    1.61
    their
    1.57
     THEIR
    1.27
    各自
    1.17
    selves
    1.15
     Leurs
    1.14
    Activations Density 0.984%

    No Known Activations