© 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-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 527
    Prev
    Next
    INDEX
    Explanations

    phrases related to identifying and managing risks, particularly in healthcare and cybersecurity contexts

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

    early prevention and onset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.43
    záll
    -0.38
     intStringLen
    -0.34
     voluntarios
    -0.33
     composés
    -0.33
    agissait
    -0.33
    ResumeLayout
    -0.32
    gebnisse
    -0.31
    znál
    -0.31
    ıklı
    -0.30
    POSITIVE LOGITS
     preventive
    0.98
     preventative
    0.98
     early
    0.94
     prevention
    0.85
     EARLY
    0.84
     Preventive
    0.83
    Preven
    0.82
    preven
    0.80
     preven
    0.80
    early
    0.79
    Activations Density 0.083%

    No Known Activations