© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2876
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental conservation and quality in products

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

    "quality" and related terms

    np_acts-logits-general · gemini-2.0-flash

    high quality and standard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.80
     مرئيه
    -0.79
     CURIAM
    -0.74
     المعيارى
    -0.58
    ">//
    -0.58
     صوتيه
    -0.57
    AndEndTag
    -0.57
     esternos
    -0.56
    principalColumn
    -0.56
    írus
    -0.55
    POSITIVE LOGITS
     quality
    3.22
    quality
    2.72
    Quality
    2.48
     Quality
    2.48
     QUALITY
    2.46
    QUALITY
    2.28
     qualité
    2.18
     calidad
    2.15
     qualidade
    2.07
     kwaliteit
    2.02
    Activations Density 0.286%

    No Known Activations