© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15154
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to distributed systems and algorithms

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

    preceding "version" or "networks"

    np_acts-logits-general · gemini-2.0-flash

    distributed versions and coupled conditional states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -1.07
    tvguidetime
    -0.95
     كومونز
    -0.92
     مشين
    -0.92
    DoubleQuotes
    -0.90
     الحره
    -0.90
    abestanden
    -0.89
     дописавши
    -0.88
     متعلقه
    -0.85
     CreateTagHelper
    -0.83
    POSITIVE LOGITS
     non
    0.80
    ness
    0.74
     versus
    0.71
     version
    0.69
    ized
    0.66
    まま
    0.66
    ITY
    0.64
    NESS
    0.62
     pula
    0.61
     or
    0.61
    Activations Density 1.810%

    No Known Activations