© 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. 3-GEMMASCOPE-RES-16K
    11. 9819
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical or scientific expressions and formal statements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     springfox
    -0.82
    󠁿
    -0.78
    ionView
    -0.77
     tslint
    -0.77
    BeginContext
    -0.76
    VolleyError
    -0.74
    Vidite
    -0.72
    OfDay
    -0.71
    ٞ
    -0.70
     IBOutlet
    -0.70
    POSITIVE LOGITS
    AutoresizingMask
    0.76
    …………………………………………
    0.65
    0.58
    0.57
    0.56
                                   
    0.56
     circumstances
    0.55
                                
    0.54
    UnsafeEnabled
    0.53
     BoxDecoration
    0.53
    Activations Density 1.213%

    No Known Activations