© 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. 40-GEMMASCOPE-RES-16K
    11. 5883
    Prev
    Next
    INDEX
    Explanations

    code elements related to user interface components and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.56
    󠁴
    -0.49
    mybatisplus
    -0.48
     оригіналу
    -0.47
    CloseOperation
    -0.46
    Manbalar
    -0.43
     intStringLen
    -0.39
    #+#
    -0.38
    ikala
    -0.38
    Vidite
    -0.38
    POSITIVE LOGITS
    DockStyle
    0.58
     Net
    0.54
     mine
    0.54
     Mine
    0.51
    Net
    0.51
     hot
    0.50
     Hot
    0.50
    Mine
    0.49
     Personal
    0.47
     net
    0.47
    Activations Density 0.136%

    No Known Activations