© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28176
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical probabilities and statistical processes

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

    P

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    '},
    -0.70
     (!__
    -0.69
    "],
    -0.69
    herr
    -0.69
     defaultstate
    -0.68
     amen
    -0.67
    OSSARY
    -0.67
    
    -0.65
     chi̍t
    -0.65
    éli
    -0.65
    POSITIVE LOGITS
     P
    1.24
    P
    1.15
     getP
    1.09
    getP
    1.05
     p
    1.00
    setP
    0.85
     său
    0.81
    nP
    0.80
     П
    0.78
     YP
    0.78
    Activations Density 0.088%

    No Known Activations