© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10345
    Prev
    Next
    INDEX
    Explanations

    phrases related to probabilities or chances of events occurring

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "chances" and following prepositions

    np_acts-logits-general · gemini-2.0-flash

    likelihood of events

    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
    Negative Logits
     سكانية
    -0.62
    genstein
    -0.54
    èlement
    -0.53
    riwal
    -0.53
    __(/*!
    -0.53
    WEBPACK
    -0.52
     AssemblyVersion
    -0.50
    ništ
    -0.50
    سطس
    -0.49
    NOSIS
    -0.49
    POSITIVE LOGITS
     chance
    0.94
     chances
    0.92
     CHANCE
    0.91
    Chances
    0.89
     propOrder
    0.88
     Chances
    0.86
     Chance
    0.84
    Chance
    0.83
    chance
    0.80
     likelihood
    0.69
    Activations Density 0.268%

    No Known Activations