© 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. 18-GEMMASCOPE-RES-16K
    11. 12035
    Prev
    Next
    INDEX
    Explanations

    elements related to the subject's personal experiences and interviews

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

    Explaining, describing, talks or tells about

    np_acts-logits-general · gemini-2.0-flash

    explaining or describing how something happened

    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
    Geplaatst
    -0.70
    newswire
    -0.55
    LookAnd
    -0.55
    heard
    -0.54
    ódó
    -0.51
    Hear
    -0.51
    Datuak
    -0.51
    hearing
    -0.50
     hears
    -0.50
    courir
    -0.50
    POSITIVE LOGITS
     explaining
    1.62
     explain
    1.58
     explained
    1.37
     describe
    1.28
     describing
    1.28
     explains
    1.27
     Explain
    1.25
    explain
    1.23
    Explain
    1.15
     describes
    1.15
    Activations Density 0.471%

    No Known Activations