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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 62200
    Prev
    Next
    INDEX
    Explanations

    references to tokens used in authentication and session management

    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
     InputDecoration
    -0.73
     ListTile
    -0.61
     Infórmanos
    -0.60
     detailsLots
    -0.59
    SequentialGroup
    -0.58
    '},
    
    -0.57
    AdapterView
    -0.57
    esModule
    -0.56
    ModelAdmin
    -0.56
    IBAction
    -0.56
    POSITIVE LOGITS
    jsonwebtoken
    0.51
     token
    0.51
     TOKEN
    0.39
    token
    0.38
     tokens
    0.37
     pulseira
    0.36
     citoy
    0.36
    føl
    0.36
     accessToken
    0.36
    tokens
    0.35
    Activations Density 0.007%

    No Known Activations