© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5615
    Prev
    Next
    INDEX
    Explanations

    concepts related to artificial intelligence and neural networks

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

    academic and technical language related to artificial intelligence, neural networks, and machine learning research.

    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
    CloseOperation
    -0.50
    出版年
    -0.50
    awtextra
    -0.44
    alanx
    -0.39
    gonic
    -0.39
    arakhand
    -0.38
    AnchorTagHelper
    -0.38
    RTDA
    -0.37
     كومونز
    -0.37
    expédition
    -0.36
    POSITIVE LOGITS
     artificial
    1.88
     AI
    1.84
     Artificial
    1.82
    Artificial
    1.70
    AI
    1.59
    artificial
    1.54
    人工智能
    1.45
     intelligence
    1.40
     künst
    1.34
    intelligence
    1.31
    Activations Density 0.203%

    No Known Activations