© 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. 33-GEMMASCOPE-RES-16K
    11. 501
    Prev
    Next
    INDEX
    Explanations

    key terms related to television shows, particularly their characteristics and associated entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.81
    +#+#
    -0.77
    rungsseite
    -0.73
    AndEndTag
    -0.72
    VersionUID
    -0.69
    enumii
    -0.68
    httphttps
    -0.68
    hyrchwyd
    -0.67
    ьаж
    -0.67
    HasForeignKey
    -0.67
    POSITIVE LOGITS
    InputBorder
    0.50
     syndrome
    0.43
    catálogo
    0.38
    mjs
    0.37
     Syndrome
    0.36
     framework
    0.35
     program
    0.35
    nesses
    0.35
    abetes
    0.35
    を果た
    0.35
    Activations Density 1.861%

    No Known Activations