© 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. 15073
    Prev
    Next
    INDEX
    Explanations

    phrases indicating additional information or insights

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

    The neuron activates strongly for the phrase "In addition to" at the beginning of sentences or clauses, particularly firing on the word "to" that follows "addition".

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

    additive transitional constructions that introduce supplementary information to a statement.

    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
     Pon
    -0.45
     extre
    -0.44
     WebDriverWait
    -0.44
     distor
    -0.44
     Xunit
    -0.43
     yyq
    -0.42
     cred
    -0.41
     Buenos
    -0.41
     luf
    -0.41
     supre
    -0.40
    POSITIVE LOGITS
     selain
    0.73
    Besides
    0.68
    Neben
    0.66
     naast
    0.65
     besides
    0.64
    besides
    0.64
    мимо
    0.60
    Selain
    0.60
     Besides
    0.60
     mellett
    0.59
    Activations Density 0.218%

    No Known Activations