© 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. 2-GEMMASCOPE-RES-16K
    11. 8513
    Prev
    Next
    INDEX
    Explanations

    terms related to various biological and pathological concepts, particularly those linked to 'ra' or 'rac' sounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------------</
    -0.38
     dud
    -0.36
    InjectMocks
    -0.33
     Punj
    -0.32
     Meilleur
    -0.31
    ∮
    -0.31
    łgorzata
    -0.31
    Pud
    -0.31
    ార్
    -0.30
    ButterKnife
    -0.30
    POSITIVE LOGITS
     ra
    1.38
    ras
    1.22
    rag
    1.19
    rah
    1.18
    rat
    1.18
     Ras
    1.18
     RA
    1.17
     Raoul
    1.16
     Rau
    1.16
    raf
    1.15
    Activations Density 0.763%

    No Known Activations