© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12971
    Prev
    Next
    INDEX
    Explanations

    information related to individuals and their roles within a specific state or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.51
     vostri
    -0.46
     étrangère
    -0.46
    rån
    -0.45
    TemporalType
    -0.43
    NullException
    -0.43
    <<"\
    -0.41
    väll
    -0.40
    Пу
    -0.40
     Rica
    -0.40
    POSITIVE LOGITS
     Theſe
    0.90
     myſelf
    0.80
     ſeveral
    0.78
     Monfieur
    0.76
     Anſ
    0.76
    THISDAY
    0.75
     Nigerians
    0.75
     Nigeria
    0.73
     Nigerian
    0.72
     Diſ
    0.71
    Activations Density 0.069%

    No Known Activations