Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103152
    Prev
    Next
    INDEX
    Explanations

    references to religious beliefs and their intersection with healthcare and individual rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Económica
    -0.33
     Untersuchung
    -0.33
     skú
    -0.31
     Verhältnisse
    -0.29
     gelap
    -0.28
     nevoie
    -0.28
    sumowanie
    -0.28
     '\\;'
    -0.28
     frumos
    -0.28
     Wahrheit
    -0.27
    POSITIVE LOGITS
    sizeCache
    0.61
    RotationOrder
    0.59
     ubiquit
    0.56
     cauſe
    0.56
     defaultstate
    0.55
    MLLoader
    0.54
    MethodManager
    0.54
    veratrol
    0.54
    ftagPool
    0.54
     resourceCulture
    0.53
    Activations Density 0.194%

    No Known Activations