© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 4279
    Prev
    Next
    INDEX
    Explanations

    terms related to waste and recycling practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.86
    rungsseite
    -0.82
     aveug
    -0.76
    LookAnd
    -0.74
    AccessorTable
    -0.70
     ویکی‌پدیا
    -0.70
    nicamente
    -0.70
     AssemblyCompany
    -0.69
    jooq
    -0.69
    antMatchers
    -0.69
    POSITIVE LOGITS
     Waste
    1.13
     waste
    1.13
     garbage
    1.07
     WASTE
    1.06
     trash
    1.06
    Waste
    1.02
    waste
    1.02
    WASTE
    0.99
     basura
    0.96
    trash
    0.94
    Activations Density 0.172%

    No Known Activations