© 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. 7685
    Prev
    Next
    INDEX
    Explanations

    references to management, guidance, and relational dynamics in various contexts

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

    sequences of proper nouns and named entities, particularly people's names and organizational titles.

    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
     chande
    -0.40
     canst
    -0.38
    tement
    -0.37
    ichtlich
    -0.36
    ukasz
    -0.35
     Pred
    -0.35
     diagon
    -0.34
     TES
    -0.34
     sais
    -0.34
     poster
    -0.34
    POSITIVE LOGITS
     accompany
    1.48
     accompanies
    1.32
     accompanying
    1.25
     acompañ
    1.16
     acompanhar
    1.12
     acompañar
    1.09
     ikut
    1.07
     conmigo
    1.06
     acompaña
    1.01
     begleiten
    0.97
    Activations Density 0.376%

    No Known Activations