© 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. 16-GEMMASCOPE-RES-16K
    11. 8325
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical values, ratings, and conditions of comparison

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

    Phrases indicating numerical comparisons

    np_acts-logits-general · gemini-2.0-flash

    less negative not

    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
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.58
    LayoutStyle
    -0.54
    tvguidetime
    -0.54
    AxisAlignment
    -0.53
    >",
    -0.52
    chae
    -0.52
    InSection
    -0.51
     Référence
    -0.50
    alline
    -0.48
    glEnable
    -0.48
    POSITIVE LOGITS
    less
    0.99
    lessness
    0.90
     less
    0.89
    lessly
    0.88
     moins
    0.82
    LESS
    0.82
     değil
    0.73
     menos
    0.73
     नहीं
    0.72
     LESS
    0.70
    Activations Density 0.929%

    No Known Activations