© 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. 12-GEMMASCOPE-RES-16K
    11. 5362
    Prev
    Next
    INDEX
    Explanations

    text related to phonological and linguistic analysis

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

    phonological or linguistic terms, especially those related to spelling, pronunciation, phonetics, and letter sounds.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    discussions of phonetics and orthography, such as sounds, letters, syllables, spelling variants, and romanization/anglicization.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    -0.62
     CreateTagHelper
    -0.61
    ConstraintMaker
    -0.57
    +#+#
    -0.56
     kasarigan
    -0.50
     snippetHide
    -0.50
     onPostExecute
    -0.50
    Xna
    -0.50
     kaarangay
    -0.50
    bufio
    -0.49
    POSITIVE LOGITS
     pronunciation
    0.57
    Pronunciation
    0.56
     pronouncing
    0.54
     pronounced
    0.53
     pronunci
    0.52
    pron
    0.49
     phonetic
    0.48
     pronounce
    0.47
     Pron
    0.47
    pronounced
    0.46
    Activations Density 0.506%

    No Known Activations