© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 12404
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to specific entities or organizations

    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
     Rollins
    -0.88
    mender
    -0.78
    slidesPer
    -0.77
    ers
    -0.76
    tieth
    -0.76
    jboss
    -0.75
     tapa
    -0.74
     TextInputType
    -0.73
     Spears
    -0.72
     StringTokenizer
    -0.72
    POSITIVE LOGITS
     Rae
    0.81
    Rae
    0.81
     IMPLIED
    0.74
     Parton
    0.70
     Stil
    0.69
    bae
    0.65
    Myth
    0.65
    Haf
    0.65
    Stil
    0.64
    pages
    0.64
    Activations Density 0.897%

    No Known Activations