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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4754
    Prev
    Next
    INDEX
    Explanations

    unique character pointers or pointer-related syntax in code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tinyos
    -0.59
    /**
    -0.56
    InjectMocks
    -0.52
    baca
    -0.48
     events
    -0.47
    keith
    -0.45
     nakalista
    -0.45
    MockBean
    -0.44
    ApiModel
    -0.43
     initComponents
    -0.43
    POSITIVE LOGITS
    قایناقلار
    0.94
     مواليد
    0.86
    قایناق‌لار
    0.83
    didSet
    0.82
    országban
    0.73
    titleMargin
    0.70
     autorytatywna
    0.67
     חיצוניים
    0.64
    sidemargin
    0.64
    unzel
    0.64
    Activations Density 0.176%

    No Known Activations