© 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. 3-GEMMASCOPE-RES-16K
    6. 6945
    Prev
    Next
    INDEX
    Explanations

    variable and attribute declaration elements in HTML or related markup languages

    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
    itter
    -0.40
    ensky
    -0.40
    údo
    -0.37
    glog
    -0.36
     itself
    -0.35
    MON
    -0.35
    Mon
    -0.35
    ⎩
    -0.34
    mon
    -0.34
    نف
    -0.34
    POSITIVE LOGITS
     &___
    1.01
     StatelessWidget
    1.00
    addCriterion
    0.91
    styleable
    0.91
    protoimpl
    0.89
    uxxxx
    0.88
    awtextra
    0.87
     getIntent
    0.87
    UIControlState
    0.87
     mapStateToProps
    0.86
    Activations Density 0.505%

    No Known Activations