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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105193
    Prev
    Next
    INDEX
    Explanations

    references to necessity and dependence on specific conditions or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     nahilalakip
    -0.38
    WebVitals
    -0.35
     ddelweddau
    -0.30
     sürd
    -0.29
     jonka
    -0.29
     selain
    -0.28
     habría
    -0.27
     sarili
    -0.27
     cantora
    -0.26
     chanteur
    -0.26
    POSITIVE LOGITS
    󠁿
    0.62
     invokingState
    0.58
     uLocal
    0.57
    ſammen
    0.56
     protoimpl
    0.56
     times
    0.56
    esModule
    0.56
    󠁬
    0.56
     occasions
    0.56
     resourceCulture
    0.55
    Activations Density 0.016%

    No Known Activations