© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 40-GEMMASCOPE-RES-16K
    11. 6987
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to symptoms, severity, and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.47
     kasarigan
    -0.47
     Мексичка
    -0.45
    tojas
    -0.45
     Besonders
    -0.42
     вікісторінку
    -0.42
     gynhyrchwyd
    -0.41
     disambiguazione
    -0.41
    Hozzáférés
    -0.40
     combineReducers
    -0.39
    POSITIVE LOGITS
     slight
    2.17
     mildly
    1.92
     slightly
    1.92
     minor
    1.91
     Slight
    1.88
    Slight
    1.86
     mild
    1.84
    slightly
    1.82
     marginally
    1.76
    mild
    1.74
    Activations Density 1.804%

    No Known Activations