© 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. 10505
    Prev
    Next
    INDEX
    Explanations

    elements of syntactic structure in language

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

    linguistic structure and grammatical parsing elements (such as syntax trees, part-of-speech tags, and dependency relations).

    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
    awtextra
    -0.87
    featureID
    -0.67
    Personendaten
    -0.63
     חיצוניים
    -0.61
     <>",
    -0.56
    WarningLevel
    -0.55
     ExecuteAsync
    -0.54
     ProtoMessage
    -0.54
    ///</
    -0.54
    makeText
    -0.54
    POSITIVE LOGITS
     verb
    1.16
     verbs
    1.07
     noun
    1.01
     adjective
    1.00
     adjectives
    0.93
     adverb
    0.92
     nouns
    0.90
     Verbs
    0.89
    verb
    0.85
     preposition
    0.85
    Activations Density 0.182%

    No Known Activations