© 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. 6395
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to account management and verification processes

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

    non-English text, particularly Cyrillic and Latin characters in localization strings and code comments.

    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
    avedra
    -0.39
    jącą
    -0.33
     sensed
    -0.32
     vindicated
    -0.32
     wytrzyma
    -0.32
     başına
    -0.31
    issippi
    -0.31
    sugges
    -0.31
    вшись
    -0.31
     suggestive
    -0.30
    POSITIVE LOGITS
     للمعارف
    0.79
    AndEndTag
    0.76
    findpost
    0.69
     дописавши
    0.67
    exitRule
    0.60
     beginnetje
    0.59
    intios
    0.59
     Biôgrafia
    0.59
    makeConstraints
    0.58
     ddelweddau
    0.58
    Activations Density 0.027%

    No Known Activations