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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1396
    Prev
    Next
    INDEX
    Explanations

    elements related to user account management and confirmation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    elements related to coding, specifically for Facebook integration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Croatian, Portuguese, and English phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Monfieur
    -1.44
     houſe
    -1.37
     pleaſure
    -1.36
     purpoſe
    -1.32
     Majefty
    -1.29
     Jefus
    -1.25
     Reſ
    -1.23
     itſelf
    -1.22
     themſelves
    -1.21
     myſelf
    -1.20
    POSITIVE LOGITS
     „
    0.61
     za
    0.59
     na
    0.52
     ist
    0.47
     «
    0.46
     z
    0.46
     los
    0.44
     k
    0.43
     bez
    0.42
     jak
    0.41
    Activations Density 0.001%

    No Known Activations