© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 12515
    Prev
    Next
    INDEX
    Explanations

    transitional phrases and prepositional phrases in the context of descriptions or narratives

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

    prepositional phrases with "in" indicating location or context.

    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
    InstrumentedTest
    -0.60
     autorytatywna
    -0.52
     mergeFrom
    -0.45
     CURLOPT
    -0.45
    AlterField
    -0.44
    ActionCreators
    -0.43
    GEBURTSDATUM
    -0.42
    transQ
    -0.42
     gynhyrchwyd
    -0.42
    Tembelea
    -0.42
    POSITIVE LOGITS
     which
    1.05
    which
    0.84
     οποία
    0.70
     lesquels
    0.65
     lequel
    0.64
     whom
    0.63
     которое
    0.61
     οποίο
    0.59
     whose
    0.59
     laquelle
    0.59
    Activations Density 1.304%

    No Known Activations