© 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. 8727
    Prev
    Next
    INDEX
    Explanations

    phrases related to support and availability of features or options in a given context

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

    words indicating limitation, restriction, or unavailability (such as "not," "available," "for," "or").

    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
    eradish
    -0.35
    mbals
    -0.34
     InputDecoration
    -0.34
    Hochspringen
    -0.30
    Pont
    -0.30
     něko
    -0.30
     antaranya
    -0.30
    󠁿
    -0.29
    ceğine
    -0.29
     někdo
    -0.28
    POSITIVE LOGITS
     all
    2.77
     semua
    2.50
     todas
    2.33
     wszystkie
    2.31
     tutte
    2.28
     kaikki
    2.22
     wszystkich
    2.19
     모든
    2.16
     всех
    2.11
     toate
    2.09
    Activations Density 2.951%

    No Known Activations