© 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. 4-GEMMASCOPE-RES-16K
    11. 10482
    Prev
    Next
    INDEX
    Explanations

    the concept of "world" and its various attributes related to its condition and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tigas
    -0.53
    tega
    -0.52
    foly
    -0.50
    onyx
    -0.49
    niejs
    -0.48
     épis
    -0.47
     rito
    -0.47
    istung
    -0.47
    TestBed
    -0.47
    ConstraintMaker
    -0.45
    POSITIVE LOGITS
     world
    2.14
     WORLD
    1.72
    world
    1.67
     World
    1.65
     wereld
    1.56
    World
    1.50
     mundo
    1.50
    WORLD
    1.49
    世界
    1.49
     dunia
    1.46
    Activations Density 0.159%

    No Known Activations