© 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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 13315
    Prev
    Next
    INDEX
    Explanations

    references to specific topics and subjects in discussions or texts

    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
     básica
    -0.35
     reconoc
    -0.33
    tauan
    -0.33
     Segen
    -0.33
     hulp
    -0.33
     darse
    -0.33
     ecológica
    -0.33
     esperamos
    -0.33
    хни
    -0.32
     Beobachtung
    -0.32
    POSITIVE LOGITS
     topics
    1.34
     topic
    1.28
     Topic
    1.13
    Topics
    1.10
     Topics
    1.10
     TOPICS
    1.03
     discussed
    1.02
     discuss
    0.99
    Topic
    0.99
     discussing
    0.98
    Activations Density 0.709%

    No Known Activations