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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 4616
    Prev
    Next
    INDEX
    Explanations

    references to political corruption and financial misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     traseiro
    -0.76
     dianteiro
    -0.71
    Manbalar
    -0.70
     abstrato
    -0.70
     móvel
    -0.68
     cartaz
    -0.67
    velmente
    -0.65
     esquerdo
    -0.64
     fundos
    -0.63
     morrer
    -0.63
    POSITIVE LOGITS
    adpleegd
    0.69
    Referências
    0.67
    VersionUID
    0.66
    Portale
    0.61
    scriptcase
    0.61
     Solidity
    0.60
    Bissau
    0.59
    Ligações
    0.58
     brazilian
    0.58
    silian
    0.56
    Activations Density 0.484%

    No Known Activations