© 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. 12-GEMMASCOPE-RES-16K
    11. 1960
    Prev
    Next
    INDEX
    Explanations

    specific categories or classifications across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasForeignKey
    -0.54
     Worth
    -0.37
     Boy
    -0.36
     Cho
    -0.36
    йки
    -0.36
     World
    -0.35
     Rose
    -0.34
     Plin
    -0.34
     Art
    -0.34
     instead
    -0.34
    POSITIVE LOGITS
     okuyayım
    0.73
     consultato
    0.66
     للاسماء
    0.61
     stiefe
    0.58
     navideños
    0.54
     Infórmanos
    0.54
     jenner
    0.54
     صوتيه
    0.53
    erráneo
    0.53
    DockStyle
    0.53
    Activations Density 3.523%

    No Known Activations