© 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. 31-GEMMASCOPE-RES-16K
    11. 7880
    Prev
    Next
    INDEX
    Explanations

    SQL queries and their components related to data selection and manipulation

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

    database table and column names in SQL queries.

    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
    脚注の使い方
    -0.72
    httphttps
    -0.67
     autorytatywna
    -0.65
    Diweddarwch
    -0.60
     CreateTagHelper
    -0.60
    存于互联网档案馆
    -0.58
    QMetaType
    -0.57
    displayquote
    -0.56
     المعيارى
    -0.56
     мәкал
    -0.55
    POSITIVE LOGITS
     where
    0.58
     AS
    0.57
     WHERE
    0.56
     left
    0.50
     order
    0.49
     as
    0.49
     AND
    0.48
     Where
    0.46
     inner
    0.44
     LEFT
    0.43
    Activations Density 0.168%

    No Known Activations