© 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. 10-GEMMASCOPE-RES-16K
    11. 11729
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to mathematical equations and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getLogin
    -0.55
    setAccessible
    -0.52
     doubtnut
    -0.52
     calcetines
    -0.52
     Efq
    -0.51
     proyección
    -0.49
     pleaſure
    -0.48
     canst
    -0.48
     você
    -0.48
     proyec
    -0.47
    POSITIVE LOGITS
     M
    0.99
    M
    0.82
     m
    0.81
     MH
    0.81
     MC
    0.75
    mybatisplus
    0.71
     MW
    0.71
     MU
    0.71
     MB
    0.70
     MV
    0.69
    Activations Density 4.541%

    No Known Activations