© 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 - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 5982
    Prev
    Next
    INDEX
    Explanations

    references to toxicity, particularly relating to chemicals and their effects on laboratory animals

    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
     चीज़ों
    -0.63
    Referințe
    -0.59
     aDecoder
    -0.48
     rū
    -0.47
     eneste
    -0.45
     dép
    -0.44
    ansky
    -0.43
    QObject
    -0.42
    مراجع
    -0.42
     معن
    -0.41
    POSITIVE LOGITS
     itſelf
    0.93
     Majefty
    0.91
    ſelf
    0.88
     Jefus
    0.86
     houſe
    0.86
     myſelf
    0.85
     raiſ
    0.83
     themſelves
    0.82
     himſelf
    0.82
     pleaſure
    0.81
    Activations Density 0.229%

    No Known Activations