© 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. 15491
    Prev
    Next
    INDEX
    Explanations

    principles of ethical communication and responsible technology use

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

    after punctuation (, or **) or "use"

    np_acts-logits-general · gemini-2.0-flash

    facilitate policy and advisory use

    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
     riuscito
    -0.63
    ंदीखरीदारी
    -0.61
     discorso
    -0.60
     anlam
    -0.59
     appunto
    -0.58
    دانشنامهٔ
    -0.58
     destinées
    -0.56
     piú
    -0.56
    Réalisation
    -0.56
     réus
    -0.53
    POSITIVE LOGITS
     defaultstate
    0.73
    NameInMap
    0.68
    IRUS
    0.65
     cost
    0.63
    何より
    0.59
     timing
    0.59
     costs
    0.59
     flexibility
    0.58
     flexible
    0.58
    GGLE
    0.56
    Activations Density 0.793%

    No Known Activations