© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11918
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific numeric formats

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

    domain names and URLs (specifically the ".com" and "amazon" parts of web addresses).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infór
    -0.59
     navideño
    -0.51
    发表于
    -0.50
     mejorado
    -0.49
     enfans
    -0.49
     vôtre
    -0.47
     Garantía
    -0.47
     nôtre
    -0.47
    httphttps
    -0.46
     ejecutivo
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    0.60
    ofire
    0.59
     pneumatic
    0.56
     Foucault
    0.54
    ticon
    0.53
    UPAC
    0.52
     ویکی‌آمباردا
    0.52
    bcryptjs
    0.52
     dodge
    0.52
     fumig
    0.52
    Activations Density 0.260%

    No Known Activations