© 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. 35-GEMMASCOPE-RES-16K
    11. 12204
    Prev
    Next
    INDEX
    Explanations

    connections between systems and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.53
    antaranya
    -0.49
    AndEndTag
    -0.47
     zijne
    -0.47
     Paglinawan
    -0.46
     voren
    -0.46
     précédents
    -0.45
     atrás
    -0.45
     antaranya
    -0.44
     übrigen
    -0.44
    POSITIVE LOGITS
     mutually
    1.31
     saling
    1.20
    互
    1.19
     interdependent
    1.13
     mutual
    1.11
     overlapping
    1.11
     intertwined
    1.08
    互相
    1.05
    相互
    1.05
     birbir
    1.04
    Activations Density 1.493%

    No Known Activations