© 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. 9636
    Prev
    Next
    INDEX
    Explanations

    terms related to reducing or alleviating negative impacts or risks

    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
     Perkins
    -0.59
    sche
    -0.55
    dig
    -0.52
    anguard
    -0.52
     Ramón
    -0.52
    --
    -0.51
    横に
    -0.51
     Ma
    -0.49
    sia
    -0.49
    ougou
    -0.48
    POSITIVE LOGITS
     mitig
    1.24
     mitigate
    1.17
     mitigated
    1.15
    setVerticalGroup
    1.14
     mitigation
    1.14
     mitigating
    1.12
     lessen
    1.03
     lessening
    1.02
     Mitigation
    1.00
     dampen
    0.98
    Activations Density 0.308%

    No Known Activations