© 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. 12298
    Prev
    Next
    INDEX
    Explanations

    conversational exchanges and dialogues

    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
     impactful
    -0.75
     tbh
    -0.73
     incentiv
    -0.68
     tasked
    -0.66
     idk
    -0.66
     emojis
    -0.66
     bestie
    -0.66
     relatable
    -0.65
     curated
    -0.65
     Idk
    -0.65
    POSITIVE LOGITS
    faßt
    0.75
     muß
    0.73
     lousy
    0.59
     müßte
    0.55
     Schluß
    0.54
     biß
    0.52
     wuß
    0.50
     quelquefois
    0.49
     mußte
    0.49
     daß
    0.47
    Activations Density 0.996%

    No Known Activations