© 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. 1275
    Prev
    Next
    INDEX
    Explanations

    numeric values and formatting in various contexts

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

    Dates with "19" followed by a number

    np_acts-logits-general · gemini-2.0-flash

    years, dates, or version numbers

    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
     Stans
    -0.55
    ticultural
    -0.51
    ற்ற
    -0.50
    醐
    -0.49
     Yarm
    -0.49
    (@"%@",
    -0.49
    enumii
    -0.48
    PointSize
    -0.46
    BindingSource
    -0.46
    uxley
    -0.46
    POSITIVE LOGITS
    Демографія
    0.60
    Pratique
    0.59
     consultato
    0.59
    Personendaten
    0.58
    CrossRef
    0.58
    askar
    0.57
     Support
    0.56
    FontOfSize
    0.56
    ellees
    0.56
    arXiv
    0.55
    Activations Density 0.302%

    No Known Activations